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. 3-RES-JB
    6. 21765
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Moussa" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or names pertinent to a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    starter
    -0.89
    breaks
    -0.79
    LIN
    -0.75
    INGTON
    -0.71
    ships
    -0.70
    tails
    -0.70
    papers
    -0.68
    gencies
    -0.67
     unaff
    -0.66
    States
    -0.65
    POSITIVE LOGITS
    pling
    1.32
    plings
    1.19
    uth
    0.98
    velength
    0.96
    uton
    0.93
    isoft
    0.92
    uble
    0.92
    ud
    0.90
    qs
    0.89
    ñ
    0.88
    Activations Density 0.007%

    No Known Activations