© 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. 11656
    Prev
    Next
    INDEX
    Explanations

    references to physical sides or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to "side," indicating a focus on dichotomies or opposing viewpoints

    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
    ãĥĺ
    -0.68
    iami
    -0.67
    bourg
    -0.63
    hots
    -0.62
    BER
    -0.62
    onga
    -0.62
     Osiris
    -0.61
    Austral
    -0.61
    etics
    -0.60
    arius
    -0.60
    POSITIVE LOGITS
     side
    3.80
     Side
    2.63
     sides
    2.48
    side
    2.31
    Side
    2.30
     sidebar
    1.37
     sided
    1.37
     flank
    1.30
     underside
    1.20
     shoulder
    1.15
    Activations Density 0.028%

    No Known Activations