© 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 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. 6-RES-JB
    11. 14748
    Prev
    Next
    INDEX
    Explanations

    phrases related to making a strong decision or commitment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to reinforcement or commitments, particularly in decision-making contexts

    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
    RAW
    -0.69
    uddin
    -0.65
    ################
    -0.64
    SEA
    -0.62
     Grade
    -0.61
     uncond
    -0.60
     USL
    -0.56
    atican
    -0.56
    bank
    -0.55
    shaw
    -0.55
    POSITIVE LOGITS
    ammy
    1.09
    eds
    0.76
    rencies
    0.72
    imester
    0.71
    fig
    0.68
    edly
    0.67
    fect
    0.67
    abytes
    0.64
    Psy
    0.63
    ï¸ı
    0.63
    Activations Density 0.096%

    No Known Activations