© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7476
    Prev
    Next
    INDEX
    Explanations

    medical terms related to hormone disorders and treatments

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.17
    0.7%
    471
    +0.12
    0.5%
    339
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.17
    151
    +0.12
    0.13
    18
    +0.12
    0.10
    Negative Logits
    asso
    -0.98
    ĸļ
    -0.97
    azaki
    -0.96
    mel
    -0.91
    ascript
    -0.88
    otide
    -0.86
    itars
    -0.86
    ERO
    -0.82
    adra
    -0.79
    acter
    -0.79
    POSITIVE LOGITS
    ness
    1.20
     persons
    1.15
     souls
    1.12
     youngsters
    1.11
     youths
    1.10
     individuals
    1.09
     households
    1.04
     idiots
    1.02
    glers
    0.97
     masses
    0.96
    Activations Density 3.145%

    No Known Activations