Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4737
    Prev
    Next
    INDEX
    Explanations

    names of places and institutions

    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
    582
    +0.14
    0.6%
    611
    +0.14
    0.6%
    701
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.14
    0.10
    659
    +0.14
    0.11
    232
    +0.13
    0.10
    Negative Logits
     carbohyd
    -0.91
     gobl
    -0.79
     mathemat
    -0.76
     distingu
    -0.74
    arcity
    -0.73
    mble
    -0.73
    ¥ŀ
    -0.73
     comprom
    -0.72
    perty
    -0.72
     skelet
    -0.71
    POSITIVE LOGITS
     Islands
    1.08
     Airways
    1.06
     Manor
    1.06
     Springs
    1.05
    ians
    1.02
     Heights
    1.01
    idae
    1.00
     Mansion
    0.99
    ian
    0.97
     Valley
    0.97
    Activations Density 1.855%

    No Known Activations