© 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. 17695
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with prices or quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to organizational or product details along with their respective identifiers or metrics

    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
    opian
    -0.88
    PASS
    -0.75
    kus
    -0.70
    oard
    -0.70
    aptic
    -0.66
    bah
    -0.66
    frog
    -0.66
    gard
    -0.66
    lux
    -0.64
    alus
    -0.64
    POSITIVE LOGITS
     Unknown
    0.80
     unknown
    0.79
     varies
    0.74
     =
    0.73
     affiliation
    0.72
    âĢİ
    0.72
     sponsor
    0.72
    specified
    0.72
    =
    0.71
    ="
    0.70
    Activations Density 0.563%

    No Known Activations