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. 5-RES-JB
    6. 10837
    Prev
    Next
    INDEX
    Explanations

    fractional values, such as measurements in halves

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific numerical values and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rine
    -0.92
    alia
    -0.81
    ories
    -0.78
    opher
    -0.77
    utical
    -0.77
    rums
    -0.77
    alus
    -0.75
    ancy
    -0.75
    uating
    -0.74
    rina
    -0.73
    POSITIVE LOGITS
    Ò
    0.77
    cffffcc
    0.73
    abouts
    0.70
     Flavoring
    0.68
    jud
    0.68
    uberty
    0.68
     hearts
    0.67
    WAYS
    0.65
     Mandela
    0.65
    xual
    0.63
    Activations Density 0.030%

    No Known Activations