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. 10732
    Prev
    Next
    INDEX
    Explanations

    words related to evaluation and judgment, indicating strong assessments and opinions

    oai_token-act-pair · gpt-3.5-turbo

    repetitive use of the verb "is" across various contexts

    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
    racuse
    -0.70
    want
    -0.70
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
    ossom
    -0.67
    inav
    -0.64
    ESE
    -0.64
    halla
    -0.64
    onnaissance
    -0.64
     Calls
    -0.64
    ukong
    -0.64
    POSITIVE LOGITS
     unlikely
    1.31
     technically
    1.24
     certainly
    1.23
    nt
    1.22
     not
    1.22
     undeniably
    1.20
     still
    1.16
     admittedly
    1.14
     definitely
    1.12
     NOT
    1.12
    Activations Density 0.483%

    No Known Activations