Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 21342
    Prev
    Next
    INDEX
    Explanations

    references to couples

    oai_token-act-pair · gpt-3.5-turbo

    references to couples

    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
     Flavoring
    -0.78
    schild
    -0.74
    é¾
    -0.71
     Directorate
    -0.66
    ibaba
    -0.61
    OUGH
    -0.61
    umbn
    -0.58
    emouth
    -0.58
    ifact
    -0.57
    ichick
    -0.57
    POSITIVE LOGITS
    hood
    0.94
     wed
    0.91
    maid
    0.88
    ndra
    0.87
     married
    0.87
    tons
    0.85
    plates
    0.83
    riages
    0.82
     divorced
    0.81
     divor
    0.80
    Activations Density 0.027%

    No Known Activations