© 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. 985
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations and people

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and locations in context

    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
    Versions
    -0.68
    RO
    -0.67
    ione
    -0.64
    ories
    -0.64
    erate
    -0.62
    flags
    -0.62
    OLD
    -0.62
    ecided
    -0.62
    process
    -0.61
     addicts
    -0.61
    POSITIVE LOGITS
     whom
    0.95
    */(
    0.78
     Symphony
    0.68
     Jr
    0.66
    etime
    0.65
    pired
    0.61
     his
    0.60
     Tens
    0.59
     Celebrity
    0.59
     behalf
    0.58
    Activations Density 0.209%

    No Known Activations