Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 22781
    Prev
    Next
    INDEX
    Explanations

    phrases indicating approval or authorization

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "sign off."

    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
    Gall
    -0.64
    ãĥĸ
    -0.63
    Export
    -0.62
     Eisenhower
    -0.59
    ãĥį
    -0.58
     Mate
    -0.58
    geries
    -0.58
    ãĥ¼ãĥĨãĤ£
    -0.57
    CU
    -0.56
    ilation
    -0.56
    POSITIVE LOGITS
    shoot
    0.89
    MENTS
    0.79
    spr
    0.79
    ments
    0.79
    MENT
    0.78
    beat
    0.78
    ment
    0.76
    cffffcc
    0.75
    undown
    0.72
    sites
    0.71
    Activations Density 0.041%

    No Known Activations