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. 4-RES-JB
    6. 5022
    Prev
    Next
    INDEX
    Explanations

    pronouns or nouns referring to people

    oai_token-act-pair · gpt-3.5-turbo

    the relative pronoun "who," indicating a focus on subjects or individuals in various contexts

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

    No Comments

    Negative Logits
    Quantity
    -0.74
    AN
    -0.62
    ======
    -0.62
    arity
    -0.60
    ANK
    -0.59
    DIT
    -0.58
    dit
    -0.58
    UNE
    -0.56
    ENN
    -0.56
    mud
    -0.56
    POSITIVE LOGITS
    hesda
    0.76
     comprises
    0.74
     accompanies
    0.73
    pires
    0.71
    ©¶æ
    0.69
     rocked
    0.69
     appealed
    0.68
     comprise
    0.67
     redes
    0.67
     benefited
    0.66
    Activations Density 0.293%

    No Known Activations