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. 10648
    Prev
    Next
    INDEX
    Explanations

    statements related to programming code and classes

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to programming and database management

    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
    theless
    -0.84
    terday
    -0.83
    ecd
    -0.79
    conservancy
    -0.76
    ischer
    -0.72
    ctica
    -0.71
    zees
    -0.69
     theaters
    -0.68
     CDs
    -0.67
    atonin
    -0.67
    POSITIVE LOGITS
    Output
    1.08
    String
    1.01
    Input
    0.99
    Node
    0.96
    Definition
    0.92
    Method
    0.92
    Result
    0.92
    Error
    0.91
    Type
    0.91
    Ut
    0.91
    Activations Density 0.146%

    No Known Activations