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. 3-RES-JB
    6. 19580
    Prev
    Next
    INDEX
    Explanations

    phrases related to the intuitive nature or usability of something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of intuitiveness or intuitive concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gre
    -0.74
    mington
    -0.73
    abad
    -0.71
    crow
    -0.69
    annis
    -0.68
    emetery
    -0.68
     Roads
    -0.68
    fighters
    -0.66
    ankind
    -0.65
    dogs
    -0.64
    POSITIVE LOGITS
    ly
    1.18
    uitive
    1.07
     intuitive
    1.06
    istically
    0.90
    ically
    0.89
    istic
    0.87
     shortcut
    0.84
     disson
    0.83
     shortcuts
    0.81
    intuitive
    0.80
    Activations Density 0.003%

    No Known Activations