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. 4995
    Prev
    Next
    INDEX
    Explanations

    mentions of different political parties and organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of entities or groups that are abbreviated as "AN"

    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
    lda
    -0.79
    ãĤ¡
    -0.76
     Cind
    -0.76
    ï¸ı
    -0.72
    odore
    -0.68
     Wink
    -0.68
    uably
    -0.68
    ments
    -0.67
     Kem
    -0.64
     guiIcon
    -0.64
    POSITIVE LOGITS
    alyst
    1.05
    igans
    1.01
    OVA
    0.97
    ufact
    0.95
    NER
    0.94
    NING
    0.93
    thood
    0.93
    ARCH
    0.91
    pour
    0.89
    TRY
    0.89
    Activations Density 0.017%

    No Known Activations