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. 2-RES-JB
    6. 17967
    Prev
    Next
    INDEX
    Explanations

    US states,

    oai_token-act-pair · gpt-3.5-turbo

    mentions of locations in the context of specific states, particularly Minnesota

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    NRS
    -0.84
    oit
    -0.79
    ounter
    -0.76
    \\\\\\\\
    -0.76
    »Ĵ
    -0.70
    far
    -0.69
    FFER
    -0.67
    ugu
    -0.67
    unity
    -0.67
    hazard
    -0.65
    POSITIVE LOGITS
    taboola
    0.68
    cius
    0.65
     Inspect
    0.60
     installments
    0.60
     Selling
    0.60
     Shopping
    0.58
     sshd
    0.58
     underest
    0.58
     telling
    0.57
     selling
    0.57
    Activations Density 0.000%

    No Known Activations