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. 1-RES-JB
    6. 16652
    Prev
    Next
    INDEX
    Explanations

    instances of the word "manual" in a technical or instructional context

    oai_token-act-pair · gpt-3.5-turbo

    references to user manuals and instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Chance
    -0.82
    apest
    -0.80
    adding
    -0.73
    REAM
    -0.72
    our
    -0.71
    Ir
    -0.70
    roud
    -0.69
    itter
    -0.69
    OUGH
    -0.67
    èª
    -0.66
    POSITIVE LOGITS
     manual
    1.16
     dexterity
    1.01
     typew
    0.91
     transmission
    0.89
     destro
    0.86
     encount
    0.83
     exha
    0.82
     describ
    0.82
     Manual
    0.79
     hemor
    0.79
    Activations Density 0.008%

    No Known Activations