© 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. 4-RES-JB
    11. 15319
    Prev
    Next
    INDEX
    Explanations

    references to specific acronyms or codes

    oai_token-act-pair · gpt-3.5-turbo

    references to social media platforms and related organizations

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

    No Comments

    Negative Logits
     Engels
    -0.75
    doms
    -0.66
    producing
    -0.63
    Coun
    -0.63
    gow
    -0.62
    toe
    -0.60
    Keefe
    -0.59
    train
    -0.58
    cock
    -0.58
    åĮ
    -0.57
    POSITIVE LOGITS
    MpServer
    0.79
    izon
    0.77
    ica
    0.77
    oro
    0.75
    apon
    0.74
    ooky
    0.73
    iac
    0.72
    artz
    0.70
    \\\\\\\\
    0.70
    thritis
    0.70
    Activations Density 0.015%

    No Known Activations