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. 6-RES-JB
    6. 24169
    Prev
    Next
    INDEX
    Explanations

    technical terms and proper nouns related to specific entities

    oai_token-act-pair · gpt-3.5-turbo

    specific structured formats or elements in text related to data or programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angel
    -0.95
    Christmas
    -0.84
    elaide
    -0.82
    abby
    -0.79
    ache
    -0.79
    comed
    -0.79
    activity
    -0.78
    organ
    -0.77
    amily
    -0.77
    sung
    -0.77
    POSITIVE LOGITS
     LX
    1.07
     Q
    1.01
     IX
    1.01
     Ti
    0.98
     XT
    0.97
     X
    0.97
     M
    0.96
     Pt
    0.95
     FN
    0.93
     N
    0.93
    Activations Density 0.314%

    No Known Activations