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. 2-RES-JB
    6. 26
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, specifically Zambia and people's names like Zhang

    oai_token-act-pair · gpt-3.5-turbo

    references to Zambia and individuals named Zhang

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of "Zamb" and "Zhang", focusing on specific proper nouns (likely related to names or places)

    oai_token-act-pair · gpt-4-turbo
    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
     Fargo
    -0.89
     Triangle
    -0.79
    ngth
    -0.77
    ãĥĪ
    -0.76
    ãĥĦ
    -0.69
     turtle
    -0.66
     triangle
    -0.65
    teness
    -0.65
     Turtle
    -0.62
    furt
    -0.62
    POSITIVE LOGITS
    Offline
    0.91
    Laughs
    0.89
    eph
    0.87
    minist
    0.86
    iano
    0.83
    iop
    0.82
    artifacts
    0.79
    iov
    0.74
    ened
    0.73
    rian
    0.72
    Activations Density 0.021%

    No Known Activations