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. 3342
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thorough" when associated with another word

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "thorough" and its related context

    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
    AIN
    -0.80
     Gleaming
    -0.67
    nesota
    -0.64
    qqa
    -0.63
     Quit
    -0.63
     Nur
    -0.63
    gdala
    -0.62
     Hots
    -0.61
    HB
    -0.61
    CHAT
    -0.61
    POSITIVE LOGITS
    bred
    1.47
    fare
    1.41
    going
    1.23
    ness
    1.23
    nesses
    1.06
    eln
    0.90
    ple
    0.88
    ances
    0.82
    abouts
    0.82
    ner
    0.80
    Activations Density 0.042%

    No Known Activations