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. 11-RES-JB
    6. 22407
    Prev
    Next
    INDEX
    Explanations

    important keywords or named entities, possibly related to news or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of 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
    Not in Any Lists

    No Comments

    Negative Logits
     heads
    -0.67
     tweak
    -0.64
     Adin
    -0.64
     Britann
    -0.63
     thousands
    -0.62
     celebr
    -0.62
     passages
    -0.61
     hundreds
    -0.61
     diapers
    -0.60
     billions
    -0.60
    POSITIVE LOGITS
    atherine
    1.40
    udos
    1.37
    eeper
    1.34
    laus
    1.33
    orea
    1.32
    EEP
    1.30
    lein
    1.30
    ramer
    1.24
    idding
    1.24
    avanaugh
    1.24
    Activations Density 0.042%

    No Known Activations