© 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. 2-RES-JB
    11. 23240
    Prev
    Next
    INDEX
    Explanations

    names or specific phrases with the word "he"

    oai_token-act-pair · gpt-3.5-turbo

    repeated uses of the pronoun "he."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hips
    -0.85
     eleph
    -0.67
    ãĥ¯
    -0.67
     Bundes
    -0.64
    Bull
    -0.63
    æĦ
    -0.62
    INGTON
    -0.62
    é¾
    -0.60
     BaseType
    -0.60
     linking
    -0.59
    POSITIVE LOGITS
    isure
    1.02
    lling
    1.00
    ather
    0.98
    gemony
    0.92
    idel
    0.90
    aton
    0.89
    aven
    0.89
    itage
    0.88
    fty
    0.87
    arer
    0.87
    Activations Density 0.037%

    No Known Activations