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. 8-RES-JB
    6. 1511
    Prev
    Next
    INDEX
    Explanations

    instances of questions that start with "Is this" or similar phrases

    oai_token-act-pair · gpt-3.5-turbo

    questions that begin with "Is this" or similar phrases indicating inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atur
    -0.90
    alties
    -0.79
    idel
    -0.73
    aneers
    -0.72
    Ń·
    -0.72
    oslav
    -0.70
    ickr
    -0.70
    iband
    -0.67
    velop
    -0.67
    arest
    -0.67
    POSITIVE LOGITS
     happen
    1.04
     happening
    0.92
     phenomenon
    0.81
     guy
    0.75
     happens
    0.72
     Happ
    0.71
     happened
    0.70
     hypothetical
    0.69
     scenario
    0.68
     occur
    0.68
    Activations Density 0.078%

    No Known Activations