© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 2655
    Prev
    Next
    INDEX
    Explanations

    words related to bladed weapons

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'k' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •words starting with k

    No Comments

    Negative Logits
     chronological
    -0.69
     Telegram
    -0.66
     chronic
    -0.63
     shortened
    -0.62
     bore
    -0.61
     degrading
    -0.60
     billions
    -0.59
     stopp
    -0.59
     extract
    -0.59
     intended
    -0.58
    POSITIVE LOGITS
    etchup
    1.56
    arate
    1.40
    udos
    1.39
    itty
    1.37
    idd
    1.36
    ratom
    1.27
    inky
    1.27
    ibble
    1.27
    orean
    1.26
    orea
    1.25
    Activations Density 0.036%

    No Known Activations