© 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. 6-RES-JB
    11. 14502
    Prev
    Next
    INDEX
    Explanations

    words associated with falling into specific categories or traps

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to falling into categories or traps

    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
    die
    -0.70
     indu
    -0.70
    cies
    -0.66
    don
    -0.65
    boys
    -0.65
    killer
    -0.63
    be
    -0.62
     banished
    -0.62
    yip
    -0.62
    warning
    -0.61
    POSITIVE LOGITS
    izoph
    0.79
     adulthood
    0.75
    qus
    0.74
    ibilities
    0.73
     Recession
    0.71
    âĸĴ
    0.70
    Role
    0.70
     obs
    0.69
     accordance
    0.69
    clusion
    0.69
    Activations Density 0.049%

    No Known Activations