© 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. 3-RES-JB
    11. 13409
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "he" and references to a male subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.72
    emale
    -0.63
    raints
    -0.62
     Moroc
    -0.59
     Vaugh
    -0.57
     Azerb
    -0.56
    farious
    -0.55
    oola
    -0.55
    aturdays
    -0.52
    ãĥ¼ãĥĨ
    -0.52
    POSITIVE LOGITS
    zbollah
    0.76
    mos
    0.74
     Majesty
    0.64
    eded
    0.59
    sych
    0.59
    bert
    0.56
    ading
    0.56
    lder
    0.55
    brew
    0.54
    gae
    0.54
    Activations Density 0.364%

    No Known Activations