© 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. 0-RES-JB
    11. 1216
    Prev
    Next
    INDEX
    Explanations

    phrases related to electronic devices or systems that have "SE" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or theme indicated by the abbreviation "SE"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ative
    -0.78
     Hogan
    -0.71
    Imp
    -0.69
    coat
    -0.68
    itious
    -0.68
    manship
    -0.67
    omic
    -0.67
    ous
    -0.66
     pomp
    -0.64
    aghan
    -0.64
    POSITIVE LOGITS
     SE
    3.49
     SW
    2.15
     NW
    1.87
     NE
    1.67
     FE
    1.31
     Southwest
    1.30
    SE
    1.30
     OCT
    1.29
     MAR
    1.09
     SIL
    1.07
    Activations Density 0.018%

    No Known Activations