© 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. 8038
    Prev
    Next
    INDEX
    Explanations

    words related to coding and technology entities or terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Sprout" project or its variants

    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
    jit
    -0.78
    amon
    -0.72
    anos
    -0.70
    ideo
    -0.70
    AMI
    -0.70
    omething
    -0.69
    arat
    -0.64
    emo
    -0.64
    ramid
    -0.64
    phan
    -0.62
    POSITIVE LOGITS
     Spr
    4.10
    Spr
    2.16
    spr
    1.69
     spr
    1.47
     SPR
    1.34
     Spray
    1.32
     sprink
    1.14
     McGr
    1.10
     Spit
    1.10
     Schw
    1.06
    Activations Density 0.021%

    No Known Activations