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. 7907
    Prev
    Next
    INDEX
    Explanations

    references to flying a plane or piloting an aircraft

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Pil" and its variations

    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
    lies
    -0.66
     favors
    -0.63
    anwhile
    -0.63
    liness
    -0.62
    rem
    -0.59
     therein
    -0.58
     signific
    -0.57
     Debor
    -0.56
     Continued
    -0.56
     rece
    -0.56
    POSITIVE LOGITS
    oted
    1.21
    chard
    1.20
    awar
    1.01
    crow
    1.00
    ots
    0.98
    oton
    0.92
    monary
    0.91
    oting
    0.91
    nington
    0.89
    cipled
    0.86
    Activations Density 0.052%

    No Known Activations