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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 8939
    Prev
    Next
    INDEX
    Explanations

    historical and contextual age references in sentences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     captcha
    -0.72
    abilia
    -0.68
     Horizon
    -0.63
     Collider
    -0.63
     DRAG
    -0.58
     organizers
    -0.55
     balance
    -0.54
     Marketplace
    -0.54
    balance
    -0.53
     contingency
    -0.53
    POSITIVE LOGITS
    ties
    1.09
    s
    1.08
     twenties
    0.99
    ixties
    0.98
    th
    0.97
    ies
    0.87
    years
    0.86
     years
    0.81
    ieth
    0.80
    something
    0.78
    Activations Density 0.063%

    No Known Activations