© 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. 1-RES-JB
    11. 24019
    Prev
    Next
    INDEX
    Explanations

    references to technology gadgets

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gadgets and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sen
    -0.82
    mary
    -0.73
    xual
    -0.71
    lease
    -0.64
     Mutual
    -0.63
    ename
    -0.62
    phase
    -0.62
     Benef
    -0.62
    ough
    -0.60
    birth
    -0.59
    POSITIVE LOGITS
     gadget
    1.51
     gadgets
    1.44
     Gadget
    1.02
    uries
    0.90
    eers
    0.87
    enegger
    0.83
    ronics
    0.83
    achev
    0.83
    ellery
    0.78
     lapt
    0.77
    Activations Density 0.011%

    No Known Activations