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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-RES-JB
    6. 8250
    Prev
    Next
    INDEX
    Explanations

    mentions of local political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to council members and discussions related to local governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !/
    -0.76
    âĵĺ
    -0.69
    ItemTracker
    -0.69
     Corinth
    -0.68
     Biological
    -0.66
     Gamb
    -0.64
     Romanian
    -0.61
     HIP
    -0.61
    aceae
    -0.60
    ENGTH
    -0.60
    POSITIVE LOGITS
    cill
    1.49
    cil
    1.02
    selling
    1.01
    plin
    0.90
     Coun
    0.88
    sels
    0.86
    rien
    0.83
    perty
    0.82
    thood
    0.81
    pl
    0.81
    Activations Density 0.025%

    No Known Activations