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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9666
    Prev
    Next
    INDEX
    Explanations

    positive news or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases discussing positive news or good things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arate
    -0.89
    ascript
    -0.84
    edIn
    -0.79
    TPPStreamerBot
    -0.78
    ismo
    -0.77
    egu
    -0.74
    renheit
    -0.73
    furt
    -0.71
    abwe
    -0.70
    zo
    -0.69
    POSITIVE LOGITS
    est
    0.87
     portion
    0.80
     thing
    0.79
     ones
    0.79
    iest
    0.78
     side
    0.76
     stuff
    0.75
     folks
    0.73
     bits
    0.73
     Reverend
    0.72
    Activations Density 0.120%

    No Known Activations