Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 22763
    Prev
    Next
    INDEX
    Explanations

    words related to physical objects and actions happening to them

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and technical terms related to mechanisms and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ranked
    -0.75
    ;;;;
    -0.74
     Helpful
    -0.67
    Interested
    -0.67
     Know
    -0.66
    ï¸
    -0.65
     Own
    -0.65
    ECA
    -0.62
     Ranked
    -0.62
    edIn
    -0.62
    POSITIVE LOGITS
     disappears
    1.08
    iest
    0.93
     becomes
    0.93
    osphere
    0.87
     ceases
    0.85
     explodes
    0.84
     goes
    0.84
     portion
    0.83
     fades
    0.83
     wasn
    0.83
    Activations Density 0.664%

    No Known Activations