© 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. 6-RES-JB
    11. 3659
    Prev
    Next
    INDEX
    Explanations

    instances of words related to slight changes or differences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "slight" indicating minimal changes or weaknesses

    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
    halla
    -0.79
    rights
    -0.78
    CDC
    -0.76
    cellent
    -0.76
    mberg
    -0.76
    ceans
    -0.72
    kamp
    -0.69
    atu
    -0.67
    gres
    -0.66
    cert
    -0.65
    POSITIVE LOGITS
     resemblance
    0.87
     slight
    0.87
     exaggeration
    0.86
     modification
    0.82
     variance
    0.81
     impression
    0.81
     annoyance
    0.80
     sway
    0.80
     hint
    0.79
     hesitation
    0.79
    Activations Density 0.021%

    No Known Activations