© 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. 3-RES-JB
    11. 3840
    Prev
    Next
    INDEX
    Explanations

    mentions of specific proper nouns or entities

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" and its prevalence in various contexts

    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
    hops
    -0.71
    âĢij
    -0.68
    iffe
    -0.64
     depended
    -0.60
    hd
    -0.57
    Joined
    -0.57
     alone
    -0.56
    strap
    -0.55
    wash
    -0.54
    let
    -0.54
    POSITIVE LOGITS
     importance
    1.02
     latest
    0.99
     possibility
    0.96
     latter
    0.93
     entire
    0.91
     earliest
    0.90
     idea
    0.88
     same
    0.87
     notion
    0.86
     difference
    0.85
    Activations Density 1.012%

    No Known Activations