© 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. 7832
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific categories or items mentioned in a list

    oai_token-act-pair · gpt-3.5-turbo

    specific alphanumeric labels or identifiers, often for categories or data points

    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
    istical
    -0.77
    gas
    -0.71
    netflix
    -0.71
    uchs
    -0.69
    pers
    -0.66
    obbies
    -0.63
    istor
    -0.62
    enium
    -0.61
    glomer
    -0.61
    Direct
    -0.61
    POSITIVE LOGITS
    FG
    0.73
    utral
    0.69
    dq
    0.67
    Ħ¢
    0.64
    qq
    0.63
    KI
    0.63
    ++)
    0.63
    q
    0.62
    MQ
    0.62
    Īè
    0.62
    Activations Density 0.229%

    No Known Activations