© 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. 6-RES-JB
    11. 846
    Prev
    Next
    INDEX
    Explanations

    keywords related to cross-platform elements or interactions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cross-platform and interdisciplinary concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BUS
    -0.71
     Pillar
    -0.69
    Stone
    -0.69
    upper
    -0.69
    Ros
    -0.68
     Breaker
    -0.66
    FIELD
    -0.66
    aday
    -0.66
    gran
    -0.65
    Nap
    -0.65
    POSITIVE LOGITS
    ism
    0.77
     endeavor
    0.76
     applications
    0.75
     collaboration
    0.74
     endeav
    0.74
     effort
    0.74
     collaborations
    0.73
     comparisons
    0.72
     cooperation
    0.72
     scenarios
    0.72
    Activations Density 0.111%

    No Known Activations