© 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. 3-RES-JB
    11. 10737
    Prev
    Next
    INDEX
    Explanations

    terms related to procedures involving splitting or division

    oai_token-act-pair · gpt-3.5-turbo

    terms related to surgical procedures or anatomical modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    duc
    -0.74
     Polo
    -0.74
     Fen
    -0.71
    bred
    -0.69
     pub
    -0.67
    creation
    -0.63
    rest
    -0.63
     ENT
    -0.62
     Rhod
    -0.62
     Eps
    -0.62
    POSITIVE LOGITS
    otom
    1.78
    otomy
    1.12
    ayers
    1.06
    ayer
    0.94
    otine
    0.91
    obile
    0.91
    ahn
    0.91
    ay
    0.90
    obiles
    0.85
    atural
    0.81
    Activations Density 0.015%

    No Known Activations