© 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. 7-RES-JB
    11. 17164
    Prev
    Next
    INDEX
    Explanations

    interesting or compelling content or titles that prompt action, such as "MUST WATCH", potentially related to news or entertainment

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating urgency or recommendations to watch content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagon
    -0.71
    Ļ½
    -0.63
    kins
    -0.62
    metics
    -0.61
    argon
    -0.60
    bara
    -0.59
     homebrew
    -0.59
    kinson
    -0.58
    onson
    -0.56
    umenthal
    -0.55
    POSITIVE LOGITS
     MUST
    0.82
    quickShipAvailable
    0.63
     WATCH
    0.63
    Interstitial
    0.61
    Live
    0.60
    AAAA
    0.60
    VEN
    0.59
    Victoria
    0.59
    Discover
    0.58
    AUT
    0.58
    Activations Density 0.017%

    No Known Activations