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. 2-RES-JB
    6. 248
    Prev
    Next
    INDEX
    Explanations

    terms related to devices used for scanning or recording

    oai_token-act-pair · gpt-4-turbo

    technical equipment related to scanning

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of scanning and tracking technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pradesh
    -0.81
    itional
    -0.72
    entimes
    -0.72
    én
    -0.71
     Kund
    -0.70
     Crimes
    -0.69
    itions
    -0.69
    hya
    -0.69
    ori
    -0.68
    rises
    -0.67
    POSITIVE LOGITS
     extraord
    0.90
     converter
    0.84
    sonian
    0.77
     scanner
    0.74
    maid
    0.74
     drawer
    0.74
     operator
    0.74
     builder
    0.73
     breaker
    0.73
     cutter
    0.73
    Activations Density 0.063%

    No Known Activations