Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 2303
    Prev
    Next
    INDEX
    Explanations

    personal pronouns indicating the writer or reader

    oai_token-act-pair · gpt-3.5-turbo

    pronouns, particularly references to "you," "I," and "we."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    blem
    -0.77
    abouts
    -0.74
    mma
    -0.74
    DOM
    -0.71
    imity
    -0.68
    planes
    -0.66
    mens
    -0.66
    emen
    -0.65
    /.
    -0.64
    gob
    -0.64
    POSITIVE LOGITS
     progresses
    0.78
     transitions
    0.69
     crow
    0.66
     prepares
    0.66
     progressed
    0.65
     matured
    0.65
     mentioned
    0.64
     phr
    0.63
     pointed
    0.63
     grow
    0.62
    Activations Density 0.091%

    No Known Activations