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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 21364
    Prev
    Next
    INDEX
    Explanations

    Russian names and surnames

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and organizations

    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
     Midwest
    -0.68
    LESS
    -0.64
     Fifth
    -0.64
     ears
    -0.60
     Wonderland
    -0.59
    Vote
    -0.59
    Assembly
    -0.59
     cushion
    -0.59
    Field
    -0.58
     Yankee
    -0.57
    POSITIVE LOGITS
    oglu
    1.40
    Äĩ
    1.37
    opoulos
    1.34
    akis
    1.29
    oulos
    1.26
    anu
    1.26
    idis
    1.24
    ÄŁ
    1.23
    ovych
    1.22
    ovic
    1.21
    Activations Density 0.232%

    No Known Activations