© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13285
    Prev
    Next
    INDEX
    Explanations

    statements that are affirming or assertive

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "is" and its variations to highlight statements about events or situations

    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
    edIn
    -0.69
     Telesc
    -0.69
    ourt
    -0.66
     Ago
    -0.66
    hoe
    -0.66
    axe
    -0.63
    uld
    -0.63
     Telescope
    -0.62
    ook
    -0.62
    veland
    -0.61
    POSITIVE LOGITS
    nt
    0.92
     definitely
    0.89
     therefore
    0.87
     not
    0.87
     bitters
    0.86
     moot
    0.85
     hereby
    0.85
     also
    0.85
     hardly
    0.79
     essentially
    0.79
    Activations Density 0.480%

    No Known Activations