Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 4577
    Prev
    Next
    INDEX
    Explanations

    time-related concepts or events, particularly focusing on countdowns

    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
    620
    +0.10
    0.6%
    274
    +0.10
    0.5%
    649
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.10
    0.17
    138
    +0.10
    0.14
    288
    +0.09
    0.21
    Negative Logits
    nered
    -0.79
    ially
    -0.76
    edly
    -0.72
    atted
    -0.68
    ional
    -0.67
    ributed
    -0.67
    inen
    -0.67
    oran
    -0.67
    lied
    -0.66
    doms
    -0.65
    POSITIVE LOGITS
     countdown
    0.74
     timer
    0.72
     clocks
    0.70
     clock
    0.69
     Clock
    0.68
     Countdown
    0.64
    clock
    0.62
     chant
    0.60
     millenn
    0.60
     brace
    0.57
    Activations Density 7.076%

    No Known Activations