© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10555
    Prev
    Next
    INDEX
    Explanations

    mentions of habits that characters have

    oai_token-act-pair · gpt-3.5-turbo

    the word "habit" and its contextual variations

    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
    ndum
    -0.72
    abad
    -0.69
     SAR
    -0.68
    gow
    -0.67
    sie
    -0.65
    ammy
    -0.64
    affer
    -0.64
    abama
    -0.63
    zac
    -0.62
    cross
    -0.62
    POSITIVE LOGITS
    ually
    1.21
    uation
    1.20
    uated
    1.10
     habits
    1.06
    uate
    0.95
    uating
    0.86
     habit
    0.83
    uates
    0.83
    ality
    0.82
    itious
    0.80
    Activations Density 0.030%

    No Known Activations