© 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. 13190
    Prev
    Next
    INDEX
    Explanations

    phrases containing the abbreviation "OS" accompanied by numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to open-source operating systems

    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
    ered
    -0.90
    ries
    -0.86
    aneous
    -0.83
    ãĥ©ãĥ³
    -0.80
    ãĤ¡
    -0.78
    ruary
    -0.74
    ry
    -0.73
    yrinth
    -0.70
    starter
    -0.69
    riet
    -0.69
    POSITIVE LOGITS
     ANGEL
    1.10
    ECTION
    0.96
    DAQ
    0.95
    metics
    0.91
    OME
    0.88
    pace
    0.88
    SI
    0.87
    HI
    0.85
    OS
    0.85
    cano
    0.84
    Activations Density 0.007%

    No Known Activations