© 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. 8-RES-JB
    11. 22416
    Prev
    Next
    INDEX
    Explanations

    programming code snippets related to data manipulation

    oai_token-act-pair · gpt-3.5-turbo

    references to content types and attributes related to digital media, especially in connection with the word "dj."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kits
    -0.81
     Austral
    -0.78
     Fifth
    -0.75
     FORM
    -0.75
     Five
    -0.74
     Caf
    -0.74
     Bened
    -0.73
     SAN
    -0.73
     USA
    -0.72
     San
    -0.71
    POSITIVE LOGITS
    rust
    1.08
    issue
    1.05
    umeric
    1.00
    rate
    0.99
    inar
    0.99
    rad
    0.98
    inct
    0.98
    leg
    0.97
    vered
    0.97
    arse
    0.97
    Activations Density 0.252%

    No Known Activations