© 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. 4-RES-JB
    11. 14849
    Prev
    Next
    INDEX
    Explanations

    phrases signaling comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "which" as it pertains to explanations or clarifications in the text

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

    No Comments

    Negative Logits
    Behind
    -0.76
    grim
    -0.73
    let
    -0.68
    rior
    -0.68
    Roaming
    -0.62
    bug
    -0.62
     Ott
    -0.62
    hat
    -0.60
    da
    -0.60
    lean
    -0.60
    POSITIVE LOGITS
    soever
    0.90
     consisted
    0.75
    akespeare
    0.75
     corresponds
    0.74
     originated
    0.73
     consists
    0.73
     exceeds
    0.73
     lasted
    0.71
     constitutes
    0.71
     resulted
    0.71
    Activations Density 0.035%

    No Known Activations