Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 16255
    Prev
    Next
    INDEX
    Explanations

    phrases related to computer programming and technical details

    oai_token-act-pair · gpt-3.5-turbo

    statements that include the verb "is," often defining or describing various subjects

    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
    Leave
    -0.66
    ear
    -0.65
    ieth
    -0.64
    luaj
    -0.61
    ederal
    -0.60
    ysis
    -0.60
    isions
    -0.60
     Hundred
    -0.59
     glances
    -0.59
    INTON
    -0.57
    POSITIVE LOGITS
     notoriously
    1.07
     definitely
    1.06
    senal
    1.05
     indeed
    1.03
     generally
    0.99
     inherently
    0.98
     often
    0.98
     basically
    0.97
     currently
    0.97
     certainly
    0.96
    Activations Density 0.325%

    No Known Activations