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. 4685
    Prev
    Next
    INDEX
    Explanations

    sentences starting with 'If' and followed by a conditional statement

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements involving the word "if" related to various risks or evaluations

    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
    Afee
    -0.81
    ãĥķ
    -0.67
    ighters
    -0.67
     Gleaming
    -0.66
     Usually
    -0.66
    ãĥ³ãĤ¸
    -0.64
    LESS
    -0.64
    "],
    -0.62
    Reply
    -0.61
    ighter
    -0.61
    POSITIVE LOGITS
     indeed
    0.87
     someday
    0.86
     somehow
    0.75
     truly
    0.73
     ever
    0.69
    eret
    0.66
     replicated
    0.63
     succeed
    0.62
     sufficiently
    0.61
    assis
    0.61
    Activations Density 0.261%

    No Known Activations