© 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. 22265
    Prev
    Next
    INDEX
    Explanations

    complex and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to complexity and places associated with certain names, particularly "Lodge."

    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
    itu
    -0.93
     pork
    -0.68
     envy
    -0.65
    riet
    -0.63
     Zi
    -0.62
    ern
    -0.62
    Luck
    -0.61
     Bang
    -0.61
     cease
    -0.61
     RI
    -0.61
    POSITIVE LOGITS
    plex
    2.04
    asons
    1.88
     Lodge
    1.64
    asonic
    1.62
     vault
    1.58
    cause
    1.43
    Cause
    1.36
    Plex
    1.35
    Reviewer
    1.21
    asonry
    1.19
    Activations Density 0.059%

    No Known Activations