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. 19620
    Prev
    Next
    INDEX
    Explanations

    phrases related to understanding or improving systems, particularly in a scientific context

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" in various contexts

    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
    uese
    -0.54
    aturdays
    -0.51
    iates
    -0.46
     Ago
    -0.46
     peg
    -0.45
    edIn
    -0.43
     assigns
    -0.43
    ividual
    -0.42
     bidder
    -0.41
     completes
    -0.41
    POSITIVE LOGITS
    Ĥİ
    0.63
    nt
    0.62
    rael
    0.59
    cussion
    0.55
     ALWAYS
    0.54
     hereby
    0.53
    SourceFile
    0.52
    chem
    0.52
     not
    0.52
     unlikely
    0.51
    Activations Density 1.121%

    No Known Activations