© 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. 9-RES-JB
    11. 4725
    Prev
    Next
    INDEX
    Explanations

    negative sentiment and calls to action related to justice and accountability

    oai_token-act-pair · gpt-3.5-turbo

    negations and prohibitions regarding actions and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MpServer
    -0.71
     VIDEOS
    -0.70
     Pars
    -0.66
    Anyway
    -0.65
    existent
    -0.64
    liner
    -0.64
    edit
    -0.63
     Rapp
    -0.63
     notices
    -0.63
     Anyway
    -0.62
    POSITIVE LOGITS
     underestimate
    0.94
     shortcuts
    0.94
     hesitate
    0.92
    ¬¼
    0.90
    Ń·
    0.89
     forget
    0.88
     overlook
    0.88
     simplistic
    0.87
     neglect
    0.87
     presume
    0.84
    Activations Density 0.355%

    No Known Activations