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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4622
    Prev
    Next
    INDEX
    Explanations

    instances of "Zar" or "Lamar" as names or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals, especially "Zar" and "Lamar."

    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
    umbn
    -0.76
    elsen
    -0.76
    anni
    -0.75
    ablishment
    -0.74
    ensive
    -0.74
    eredith
    -0.74
    outheastern
    -0.74
    issions
    -0.73
    aucuses
    -0.73
    itionally
    -0.73
    POSITIVE LOGITS
    \\\\\\\\
    0.79
    zag
    0.74
    halla
    0.73
    zig
    0.70
     TAMADRA
    0.69
    \\\\\\\\\\\\\\\\
    0.68
    quel
    0.68
     hazard
    0.66
     Loch
    0.65
    teenth
    0.64
    Activations Density 0.050%

    No Known Activations