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. 9-RES-JB
    6. 8526
    Prev
    Next
    INDEX
    Explanations

    references to very small or tiny things

    oai_token-act-pair · gpt-3.5-turbo

    references to small or tiny objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anship
    -0.88
    thood
    -0.87
    chool
    -0.83
    gaming
    -0.78
    enario
    -0.77
    Econom
    -0.76
    arenthood
    -0.76
    ploma
    -0.74
    Nation
    -0.72
    isine
    -0.72
    POSITIVE LOGITS
     buttons
    1.32
     arrows
    1.22
     holes
    1.21
     protr
    1.21
     dots
    1.20
     markings
    1.20
     spikes
    1.19
     bubbles
    1.19
     beads
    1.13
     seams
    1.12
    Activations Density 0.486%

    No Known Activations