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. 7-RES-JB
    6. 12858
    Prev
    Next
    INDEX
    Explanations

    references to specific people and names in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns, possibly related to names, locations, or organizations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sqor
    -0.74
     Cla
    -0.74
    mental
    -0.74
    CHAR
    -0.70
    Hung
    -0.69
     sal
    -0.67
     meters
    -0.66
     155
    -0.66
     Miranda
    -0.65
     151
    -0.65
    POSITIVE LOGITS
    ocy
    1.13
    oad
    1.12
    ow
    1.11
    ó
    1.08
    os
    1.08
    Åį
    1.06
    ou
    1.06
    opa
    1.05
    o
    1.04
    ov
    1.04
    Activations Density 0.216%

    No Known Activations