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. 0-RES-JB
    6. 21011
    Prev
    Next
    INDEX
    Explanations

    words related to serious or significant tasks or endeavors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to important actions or responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BI
    -0.70
    chev
    -0.70
    ilan
    -0.70
     gel
    -0.69
    bay
    -0.67
    bil
    -0.67
    alus
    -0.66
    pak
    -0.66
     Slot
    -0.64
    raq
    -0.63
    POSITIVE LOGITS
     undert
    2.59
     undertaking
    2.53
     Advocate
    1.66
     emb
    1.35
    ilst
    1.25
     outp
    1.08
     Titanic
    1.05
     airing
    1.02
     proceeding
    0.97
     exh
    0.93
    Activations Density 0.040%

    No Known Activations