© 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. 10-RES-JB
    11. 24460
    Prev
    Next
    INDEX
    Explanations

    words related to action, especially in a dynamic or impactful context

    oai_token-act-pair · gpt-3.5-turbo

    key elements or descriptors related to media content and its analysis

    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
    Ĥ
    -0.81
    ̶
    -0.76
    ª
    -0.75
    orate
    -0.73
    ¬
    -0.73
    both
    -0.73
    ãĥĥãĥī
    -0.72
    adra
    -0.72
    same
    -0.71
    ¾
    -0.70
    POSITIVE LOGITS
     Records
    0.99
     Productions
    0.99
     Strategies
    0.96
     Technique
    0.92
     Studios
    0.92
     Calculator
    0.92
     Syndrome
    0.91
     Brewing
    0.91
     Profile
    0.91
     Approach
    0.89
    Activations Density 0.419%

    No Known Activations