© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 18568
    Prev
    Next
    INDEX
    Explanations

    items and locations in a gritty, urban setting

    oai_token-act-pair · gpt-3.5-turbo

    elements associated with chaotic or tumultuous environments

    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
    Qual
    -0.79
    TPPStreamerBot
    -0.76
    Assistant
    -0.76
     criteria
    -0.73
    Relations
    -0.73
    Secondly
    -0.70
    ISA
    -0.69
    Active
    -0.69
    Focus
    -0.68
    Commission
    -0.67
    POSITIVE LOGITS
     abound
    1.11
    hips
    1.10
    creen
    1.09
    hops
    1.07
    uits
    1.05
    mith
    1.04
     overflowing
    0.99
    hell
    0.97
    paces
    0.97
    pots
    0.97
    Activations Density 0.455%

    No Known Activations