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. 6847
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is required or necessary

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "need" and its variations

    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
    soType
    -0.68
    cession
    -0.67
    luaj
    -0.65
    peed
    -0.63
     Democr
    -0.63
    ight
    -0.62
    gdala
    -0.61
     Lowell
    -0.60
     Vaj
    -0.59
    brook
    -0.59
    POSITIVE LOGITS
    lessly
    1.25
    nces
    0.69
    xus
    0.68
    ache
    0.68
    igslist
    0.68
    LY
    0.67
    oppers
    0.67
    HAEL
    0.65
    LESS
    0.64
    n
    0.64
    Activations Density 0.061%

    No Known Activations