© 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. 0-RES-JB
    11. 2811
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ban"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ban" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iewicz
    -0.72
    ENTS
    -0.72
    tesy
    -0.69
    İĭ
    -0.68
     Pearce
    -0.68
    ateral
    -0.67
    yg
    -0.66
    enter
    -0.66
    ector
    -0.66
    aligned
    -0.65
    POSITIVE LOGITS
     ban
    3.72
     bans
    2.71
     banning
    2.30
    Ban
    2.24
     Ban
    2.15
    ban
    2.10
     banned
    2.00
     prohibition
    1.87
     Bans
    1.79
     moratorium
    1.76
    Activations Density 0.026%

    No Known Activations