© 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. 9-RES-JB
    11. 11190
    Prev
    Next
    INDEX
    Explanations

    descriptions or explanations within text

    oai_token-act-pair · gpt-3.5-turbo

    instances of descriptions or elaborations of events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osponsors
    -0.70
    onga
    -0.67
     Governors
    -0.61
    allery
    -0.60
     Events
    -0.60
     Releases
    -0.60
     Cases
    -0.60
    inances
    -0.59
     Posts
    -0.59
     Facilities
    -0.58
    POSITIVE LOGITS
     reminiscent
    1.08
     laced
    1.03
     resembling
    1.02
     explaining
    1.01
     headlined
    0.98
     detailing
    0.95
     outlining
    0.94
     illustrating
    0.92
     denouncing
    0.92
     describing
    0.91
    Activations Density 0.394%

    No Known Activations