© 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. 20477
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is not allowed or forbidden

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating restrictions or bans

    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
     Moment
    -0.69
     Cassidy
    -0.66
    agger
    -0.66
    icka
    -0.65
    pop
    -0.65
    apper
    -0.64
    appers
    -0.64
    herty
    -0.64
    lab
    -0.63
    prise
    -0.63
    POSITIVE LOGITS
     prohibited
    3.60
     forbidden
    2.63
     banned
    2.28
     barred
    2.16
     outlawed
    2.00
     prohibitions
    1.83
     prohibits
    1.80
     prohibit
    1.76
     forbid
    1.71
     prohibiting
    1.69
    Activations Density 0.022%

    No Known Activations