© 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. 39980
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertain or anticipated events

    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
    38
    +0.12
    0.5%
    274
    +0.12
    0.5%
    164
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.09
    38
    +0.12
    0.08
    200
    +0.12
    0.08
    Negative Logits
    osal
    -0.83
    heim
    -0.78
    ullah
    -0.75
     Horus
    -0.75
    rique
    -0.75
    uli
    -0.74
    aments
    -0.72
    ises
    -0.72
    essa
    -0.71
    osa
    -0.71
    POSITIVE LOGITS
    Ń·
    1.00
    ãĥ£
    0.87
     downhill
    0.85
    verning
    0.84
     bankrupt
    0.83
    -+
    0.82
     nowhere
    0.81
    ±
    0.79
    Īè
    0.79
     exha
    0.77
    Activations Density 5.268%

    No Known Activations