© 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 Local
    9. 6-RES_SCL-AJT
    11. 4038
    Prev
    Next
    INDEX
    Explanations

    names or references to a person named Rob

    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
    447
    +0.18
    0.8%
    527
    +0.15
    0.7%
    376
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    143
    +0.18
    0.06
    527
    +0.15
    0.03
    597
    +0.13
    0.05
    Negative Logits
    WAYS
    -0.90
    uated
    -0.73
     Corpus
    -0.73
    ç¥ŀ
    -0.72
    SEE
    -0.72
     fluoride
    -0.71
     halls
    -0.70
     è£ıè¦ļéĨĴ
    -0.68
    Reloaded
    -0.67
    ":[
    -0.67
    POSITIVE LOGITS
    bie
    1.17
    otics
    1.12
    bery
    1.09
    bing
    1.07
    shaw
    1.07
    bers
    1.03
    otic
    1.03
    otech
    1.02
    ooth
    1.01
    roach
    0.99
    Activations Density 5.706%

    No Known Activations