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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5479
    Prev
    Next
    INDEX
    Explanations

    phrases related to being a part of a group or community

    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
    216
    +0.15
    0.5%
    679
    +0.14
    0.5%
    236
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    676
    +0.15
    0.06
    236
    +0.14
    0.05
    597
    +0.14
    0.04
    Negative Logits
    20439
    -1.06
    culosis
    -1.01
    ITH
    -0.97
     destro
    -0.94
    berus
    -0.89
     ceilings
    -0.89
    akespe
    -0.89
    ricanes
    -0.86
    olesc
    -0.85
     nodd
    -0.83
    POSITIVE LOGITS
    ners
    1.14
    nered
    1.09
    aking
    1.05
    heartedly
    1.00
    ICLE
    0.97
    lying
    0.97
    ioned
    0.96
    ials
    0.95
    ially
    0.94
    icular
    0.94
    Activations Density 0.640%

    No Known Activations