© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 14934
    Prev
    Next
    INDEX
    Explanations

    phrases related to broad and impactful events or changes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of extensive influence or consequences

    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
    nery
    -0.83
    gged
    -0.73
     Detection
    -0.70
    gnu
    -0.68
    BU
    -0.65
    ubes
    -0.64
    gars
    -0.64
     Feet
    -0.62
    skip
    -0.62
     Cue
    -0.61
    POSITIVE LOGITS
     expans
    0.80
     neoc
    0.78
    ranging
    0.77
    rontal
    0.75
    itarian
    0.74
    reaching
    0.74
     advers
    0.74
     geopolitical
    0.74
     implications
    0.73
    ortment
    0.72
    Activations Density 0.019%

    No Known Activations