© 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. 11-RES-JB
    11. 2376
    Prev
    Next
    INDEX
    Explanations

    quotes or statements attributed to individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotation attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venth
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.57
    ãĥ¼ãĥĨ
    -0.55
     pione
    -0.54
    illions
    -0.53
    irrel
    -0.52
     conflic
    -0.51
    agn
    -0.51
    Pont
    -0.50
    UTH
    -0.50
    POSITIVE LOGITS
    :
    0.78
    :]
    0.74
     goodbye
    0.73
    :'
    0.70
    :"
    0.69
    ]:
    0.68
     he
    0.68
     Wednesday
    0.64
     she
    0.63
    .:
    0.62
    Activations Density 0.176%

    No Known Activations