© 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. 6527
    Prev
    Next
    INDEX
    Explanations

    words related to personal opinions and statements

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names

    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
    lihood
    -0.77
     disproportion
    -0.69
    ardless
    -0.67
    Issue
    -0.64
     privile
    -0.63
    ktop
    -0.60
    ãĥij
    -0.59
    actly
    -0.59
     stripping
    -0.56
     bookmark
    -0.55
    POSITIVE LOGITS
     told
    1.41
     said
    1.39
     joked
    1.23
     remarked
    1.18
     replied
    1.12
     explained
    1.12
     recalled
    1.12
     says
    1.11
     exclaimed
    1.11
     tells
    1.09
    Activations Density 0.092%

    No Known Activations