© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 24062
    Prev
    Next
    INDEX
    Explanations

    references to collaboration or conflict in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to collaborations or partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )"
    -0.72
    tein
    -0.61
    andum
    -0.59
    arta
    -0.58
     *)
    -0.58
     Dise
    -0.57
     )]
    -0.55
    )*
    -0.54
     `
    -0.54
     '[
    -0.54
    POSITIVE LOGITS
     nonetheless
    0.76
     downright
    0.70
     awfully
    0.65
    —
    0.64
     anyway
    0.60
    etheless
    0.57
     quir
    0.57
     altogether
    0.55
     superhero
    0.55
     darn
    0.55
    Activations Density 2.092%

    No Known Activations