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. 9000
    Prev
    Next
    INDEX
    Explanations

    mentions of future timeframes

    oai_token-act-pair · gpt-3.5-turbo

    references to upcoming time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ooters
    -0.76
    gor
    -0.74
    wright
    -0.72
    mel
    -0.70
    avorite
    -0.69
    ername
    -0.68
    urtles
    -0.67
    tha
    -0.66
    then
    -0.66
    usted
    -0.66
    POSITIVE LOGITS
     weeks
    1.65
     months
    1.53
     days
    1.47
     years
    1.31
     decades
    1.22
     generations
    1.19
     phases
    1.12
     seasons
    1.11
     decade
    1.10
     week
    1.08
    Activations Density 0.037%

    No Known Activations