© 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. 3-RES-JB
    11. 10680
    Prev
    Next
    INDEX
    Explanations

    technical terms related to verification processes and systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to verification and assessment processes

    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
    maxwell
    -0.56
    hiro
    -0.55
     acknow
    -0.54
    姫
    -0.52
    é¾įå
    -0.51
     FANTASY
    -0.51
    âķIJâķIJ
    -0.49
     seiz
    -0.49
    aucas
    -0.49
     notor
    -0.46
    POSITIVE LOGITS
    naire
    0.68
    eers
    0.60
    aires
    0.51
    eering
    0.50
     extraord
    0.49
     Liberia
    0.49
     outfit
    0.47
    naires
    0.46
    ants
    0.46
     ('
    0.45
    Activations Density 1.649%

    No Known Activations