© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 10217
    Prev
    Next
    INDEX
    Explanations

    specific entities such as companies, organizations, teams, and divisions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific entities or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hern
    -0.63
    wn
    -0.59
     Begin
    -0.58
     kidding
    -0.57
     Bere
    -0.57
     Hil
    -0.56
    sbm
    -0.52
     patience
    -0.52
     appre
    -0.52
     Gunn
    -0.52
    POSITIVE LOGITS
     or
    0.93
     denomination
    0.86
     imaginable
    0.84
     combinations
    0.83
     group
    0.80
    group
    0.80
     affiliation
    0.79
     depending
    0.79
     category
    0.77
     locale
    0.77
    Activations Density 0.304%

    No Known Activations