© 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 EvalsExportsinterp-engineNEWAPI 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. 5167
    Prev
    Next
    INDEX
    Explanations

    phrases related to sources or origins

    oai_token-act-pair · gpt-3.5-turbo

    references to the source of various media or content

    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
    bably
    -0.83
    merce
    -0.81
    mun
    -0.80
    pose
    -0.80
    perty
    -0.79
    ratulations
    -0.77
    mere
    -0.72
    few
    -0.71
    opausal
    -0.70
    vacc
    -0.69
    POSITIVE LOGITS
     afar
    1.37
     whence
    0.89
     anywhere
    0.83
     inside
    0.82
     antiquity
    0.77
     scratch
    0.74
     nowhere
    0.73
     underneath
    0.72
     scrimmage
    0.72
     abroad
    0.72
    Activations Density 0.132%

    No Known Activations