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. 12-RES-JB
    6. 14504
    Prev
    Next
    INDEX
    Explanations

    statements related to scientific findings and discoveries

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    details concerning legal matters and changes in regulations or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "}],"
    -0.84
    "},{"
    -0.78
    })
    -0.77
    âĢ
    -0.75
    },
    -0.69
    )\
    -0.67
     âĢ¢
    -0.67
    '';
    -0.66
    ,''
    -0.65
    )</
    -0.65
    POSITIVE LOGITS
    arently
    0.83
     "â̦
    0.83
    itled
    0.73
     omin
    0.71
     "#
    0.71
     supposedly
    0.70
    senal
    0.70
    CLUS
    0.70
    ensical
    0.69
    umably
    0.69
    Activations Density 1.305%

    No Known Activations