© 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. 45806
    Prev
    Next
    INDEX
    Explanations

    phrases related to large landscape descriptions, particularly panoramic views

    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
    641
    +0.12
    0.6%
    546
    +0.10
    0.5%
    37
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.12
    0.07
    379
    +0.10
    0.13
    584
    +0.10
    0.09
    Negative Logits
    owship
    -0.71
    >:
    -0.67
    BIL
    -0.65
    FTWARE
    -0.61
    kind
    -0.60
    gotten
    -0.60
    self
    -0.59
    Anonymous
    -0.59
     Shepard
    -0.57
    ktop
    -0.56
    POSITIVE LOGITS
    monary
    0.78
    urst
    0.73
    uese
    0.72
    olate
    0.68
    amic
    0.65
    姫
    0.65
     Tycoon
    0.63
    ieri
    0.63
    emn
    0.61
    vic
    0.61
    Activations Density 13.586%

    No Known Activations