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. 1-RES-JB
    6. 11117
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a requirement for something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "needed" in various contexts related to necessity or requirement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oller
    -0.69
    ning
    -0.69
    bow
    -0.64
     Lowell
    -0.63
    orbit
    -0.63
    washer
    -0.63
    oret
    -0.63
    kay
    -0.63
    brook
    -0.63
    bows
    -0.62
    POSITIVE LOGITS
     guiActiveUn
    0.83
    igslist
    0.81
    ulkan
    0.76
     destro
    0.74
    lessly
    0.72
     rall
    0.66
    aeda
    0.66
    --+
    0.66
    =$
    0.66
    CLASSIFIED
    0.65
    Activations Density 0.016%

    No Known Activations