© 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. 1-RES-JB
    11. 1051
    Prev
    Next
    INDEX
    Explanations

    phrases related to repeated actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    references to "habits" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.82
    ammy
    -0.80
     SAR
    -0.77
    cross
    -0.72
     RIS
    -0.71
    govtrack
    -0.66
    merce
    -0.65
    stretched
    -0.63
    angered
    -0.63
     GOODMAN
    -0.62
    POSITIVE LOGITS
     habit
    1.37
     habits
    1.07
    uated
    1.03
    ually
    0.97
    uate
    0.95
    uation
    0.89
    uates
    0.87
    uating
    0.77
     droid
    0.71
    ierre
    0.69
    Activations Density 0.004%

    No Known Activations