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. 4-RES-JB
    6. 17756
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is completely filled or characterized by a particular quality

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating abundance or fullness

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

    No Comments

    Negative Logits
    ARS
    -0.71
    Ń·
    -0.67
    aret
    -0.65
    XL
    -0.63
    offset
    -0.63
    UA
    -0.62
    ramids
    -0.62
    ARC
    -0.61
    bet
    -0.61
     escalate
    -0.60
    POSITIVE LOGITS
     juicy
    0.74
     sorts
    0.70
     surprises
    0.69
     fresh
    0.67
     sunny
    0.66
     passionate
    0.65
    amaz
    0.63
     seasoned
    0.62
     Conv
    0.61
    eworthy
    0.60
    Activations Density 0.070%

    No Known Activations