© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 9302
    Prev
    Next
    INDEX
    Explanations

    words indicating likelihood or possibility

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and future-oriented statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     culminating
    -0.66
    ngth
    -0.63
     reper
    -0.61
     progressing
    -0.61
    conom
    -0.57
     dilig
    -0.56
    rahim
    -0.56
     ascending
    -0.56
     merry
    -0.52
     motivating
    -0.52
    POSITIVE LOGITS
    None
    1.29
    not
    1.28
     not
    1.27
    none
    1.25
     never
    1.23
    Not
    1.22
     didn
    1.22
     NOT
    1.20
     none
    1.20
     nowhere
    1.18
    Activations Density 1.268%

    No Known Activations