© 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. 13757
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking information or solutions in various contexts

    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
    117
    +0.14
    0.5%
    581
    +0.14
    0.5%
    106
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    106
    +0.14
    0.08
    206
    +0.14
    0.06
    113
    +0.13
    0.06
    Negative Logits
    ENGTH
    -0.93
    imgur
    -0.91
    olid
    -0.90
    200000
    -0.89
    Merit
    -0.89
    hibition
    -0.85
    rid
    -0.85
    clusive
    -0.85
    ERO
    -0.85
    parable
    -0.85
    POSITIVE LOGITS
     whom
    0.95
    iaries
    0.91
    doms
    0.90
     inhabit
    0.90
     spouses
    0.88
     alike
    0.87
    edIn
    0.86
     illegally
    0.85
    iris
    0.84
     themselves
    0.83
    Activations Density 2.384%

    No Known Activations