© 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. 2-RES-JB
    11. 17880
    Prev
    Next
    INDEX
    Explanations

    terms related to nondiscrimination policies or activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to non-discrimination and associated concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Package
    -0.89
    ================
    -0.74
     Seat
    -0.70
    =-=-=-=-=-=-=-=-
    -0.68
     Tigers
    -0.68
     Inquisition
    -0.66
     Mercury
    -0.65
     Tune
    -0.65
     Forge
    -0.65
     Opera
    -0.64
    POSITIVE LOGITS
    etheless
    1.03
    oub
    1.01
    oubted
    0.97
    ouble
    0.97
    icol
    0.95
    entially
    0.93
    esc
    0.92
    airy
    0.90
    imensional
    0.88
    isc
    0.87
    Activations Density 0.006%

    No Known Activations