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. 11-RES-JB
    6. 10954
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Bell"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Bell."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llers
    -0.64
    rers
    -0.63
    bered
    -0.63
    joining
    -0.58
    REDACTED
    -0.58
     DUI
    -0.58
    ALLY
    -0.58
     Sochi
    -0.57
     IU
    -0.55
     Norn
    -0.55
    POSITIVE LOGITS
    amy
    1.47
    ows
    1.20
    ingham
    1.19
    ichick
    1.19
    south
    1.13
    anca
    1.05
    owed
    1.01
    aire
    0.98
    hops
    0.94
    icer
    0.94
    Activations Density 0.036%

    No Known Activations