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. 0-RES-JB
    6. 4017
    Prev
    Next
    INDEX
    Explanations

    passphrases or keywords related to programming and coding

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Pass" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     organizer
    -0.71
     Hodg
    -0.69
     disciplines
    -0.65
     organ
    -0.64
     Dillon
    -0.63
     size
    -0.62
     TED
    -0.61
     cage
    -0.60
     reserve
    -0.60
     roundup
    -0.59
    POSITIVE LOGITS
    Pass
    4.02
    PASS
    1.68
    pass
    1.39
    Active
    1.24
    Cooldown
    1.15
    Lear
    1.12
    Giving
    1.11
    Sold
    1.09
    Forward
    1.08
     PASS
    1.07
    Activations Density 0.018%

    No Known Activations