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. 1-RES-JB
    6. 7803
    Prev
    Next
    INDEX
    Explanations

    numbers related to political positions or quantitative details

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 45 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascus
    -0.94
    raltar
    -0.84
    undai
    -0.83
    hers
    -0.82
    cles
    -0.77
    MSN
    -0.75
    Reviewer
    -0.74
    gebra
    -0.73
    uve
    -0.70
    cled
    -0.69
    POSITIVE LOGITS
    678
    0.91
    %:
    0.86
    45
    0.86
    %-
    0.81
     minutes
    0.80
     ILCS
    0.80
     mins
    0.79
    ACP
    0.79
    345
    0.77
    rpm
    0.77
    Activations Density 0.026%

    No Known Activations