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. 9-RES-JB
    6. 4413
    Prev
    Next
    INDEX
    Explanations

    sentences containing the phrase "It's not"

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions of denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    former
    -0.80
    ixel
    -0.72
    umbnail
    -0.66
    izont
    -0.66
    åº
    -0.65
    papers
    -0.65
    continue
    -0.64
    ourses
    -0.64
    umbn
    -0.63
    itcher
    -0.63
    POSITIVE LOGITS
     uncommon
    1.25
    icable
    1.25
     advisable
    1.10
     easy
    1.08
     necessarily
    1.06
     unreasonable
    1.05
     surprising
    1.02
     feasible
    0.99
     raining
    0.99
     clear
    0.97
    Activations Density 0.087%

    No Known Activations