© 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. 8-RES-JB
    11. 18505
    Prev
    Next
    INDEX
    Explanations

    time-related events or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "when."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agin
    -0.75
    bear
    -0.74
    ertain
    -0.69
    age
    -0.69
    ãĤ§
    -0.68
    augh
    -0.67
    zik
    -0.67
    stay
    -0.66
    ãĥ¼ãĥ
    -0.65
    ird
    -0.63
    POSITIVE LOGITS
    soever
    1.06
     they
    0.78
     confronted
    0.75
     comparing
    0.71
     compared
    0.70
     faced
    0.70
     someone
    0.69
     suddenly
    0.68
     hordes
    0.65
     she
    0.65
    Activations Density 0.123%

    No Known Activations