© 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. 489
    Prev
    Next
    INDEX
    Explanations

    proper nouns preceded by an apostrophe

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'O' followed by an apostrophe

    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
     eclipse
    -0.78
    etheless
    -0.74
    vg
    -0.65
     inhibited
    -0.65
    anwhile
    -0.63
    »Ĵ
    -0.62
    cius
    -0.62
    urers
    -0.62
     thrill
    -0.62
    asers
    -0.61
    POSITIVE LOGITS
    Brien
    1.00
    Connor
    0.97
    clock
    0.89
    Neill
    0.89
    Malley
    0.87
    Donnell
    0.86
    Leary
    0.82
    Rah
    0.79
    kay
    0.77
    Reilly
    0.77
    Activations Density 0.015%

    No Known Activations