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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13508
    Prev
    Next
    INDEX
    Explanations

    medical conditions and anatomical terms related to the human body

    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
    167
    +0.21
    0.7%
    389
    +0.13
    0.4%
    346
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.09
    555
    +0.13
    0.05
    167
    +0.13
    0.01
    Negative Logits
    nown
    -1.01
    Reviewer
    -1.00
    EStream
    -0.99
    ãĤ¬
    -0.98
    ï¸
    -0.97
    ×Ķ
    -0.95
    UGE
    -0.95
    STER
    -0.94
    BSD
    -0.92
    ħĭ
    -0.88
    POSITIVE LOGITS
    ainment
    1.49
    ribution
    1.41
    ributed
    1.34
    ribute
    1.34
    ents
    1.34
    roversial
    1.31
    rast
    1.30
    acts
    1.25
    rovers
    1.25
    ribut
    1.24
    Activations Density 1.420%

    No Known Activations