© 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 EvalsExportsAPI 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 Local
    9. 6-RES_SCL-AJT
    11. 33593
    Prev
    Next
    INDEX
    Explanations

    geographical and astronomical references and terminology

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    315
    +0.13
    0.6%
    165
    +0.10
    0.4%
    709
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.13
    0.06
    289
    +0.10
    -0.04
    620
    +0.10
    0.01
    Negative Logits
     psychiat
    -0.71
    EStream
    -0.69
     slump
    -0.69
    bec
    -0.68
     Saban
    -0.65
     favourable
    -0.63
    ipeg
    -0.63
     Cheong
    -0.62
    ĸļ
    -0.61
    posing
    -0.61
    POSITIVE LOGITS
    ioxide
    0.77
     Trans
    0.76
    ombat
    0.74
    士
    0.73
    achus
    0.71
     Dragonbound
    0.71
    uga
    0.70
     Railway
    0.70
    dot
    0.68
    sic
    0.68
    Activations Density 11.608%

    No Known Activations