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. 8071
    Prev
    Next
    INDEX
    Explanations

    verbs indicating action or application of something to a specific object or context

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to processes or actions that are being taken or executed

    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
    ajo
    -0.77
    ylum
    -0.66
     Vaughan
    -0.65
    Doctors
    -0.62
    Irish
    -0.62
    iland
    -0.61
    anmar
    -0.61
    ierre
    -0.61
    eah
    -0.60
    paio
    -0.60
    POSITIVE LOGITS
     properly
    0.95
     correctly
    0.78
     individually
    0.77
     incorrectly
    0.70
     exceeds
    0.68
     perpend
    0.67
    });
    0.65
     scientifically
    0.64
     improperly
    0.64
     numer
    0.61
    Activations Density 0.087%

    No Known Activations