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. 7-RES-JB
    6. 24421
    Prev
    Next
    INDEX
    Explanations

    the dot character followed by a sequence of numbers that represents a version

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     purse
    -0.85
     striking
    -0.73
     framing
    -0.70
     preventive
    -0.68
    iru
    -0.68
     worsh
    -0.68
     affili
    -0.65
     ambul
    -0.65
     shutter
    -0.64
     gull
    -0.64
    POSITIVE LOGITS
    0
    1.23
    5
    1.14
    6
    1.02
    7
    1.01
    8
    0.99
    9
    0.97
    3
    0.97
    02
    0.97
    04
    0.97
    4
    0.96
    Activations Density 0.059%

    No Known Activations