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. 6-RES-JB
    6. 9437
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or entities with the initials "CM" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to "Chief Minister" (CM) in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.88
     sidx
    -0.79
    ãĥ¼ãĥĨ
    -0.75
    spell
    -0.74
    via
    -0.74
     Machina
    -0.73
    rets
    -0.73
    furt
    -0.73
    glers
    -0.73
    ibility
    -0.72
    POSITIVE LOGITS
    ODE
    0.87
     Punk
    0.80
    HC
    0.77
    apper
    0.77
    ancel
    0.76
    OUNT
    0.76
    OS
    0.74
    AMP
    0.73
    trop
    0.71
    oly
    0.69
    Activations Density 0.011%

    No Known Activations