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. 23850
    Prev
    Next
    INDEX
    Explanations

    instances of the term 'external'

    oai_token-act-pair · gpt-3.5-turbo

    references to external elements or factors

    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
    lov
    -0.83
    Merit
    -0.81
    otto
    -0.76
    kind
    -0.72
     Booker
    -0.71
    bey
    -0.71
    era
    -0.70
    lees
    -0.68
    bet
    -0.68
    kamp
    -0.68
    POSITIVE LOGITS
     external
    3.53
     External
    2.80
    external
    2.70
    External
    2.68
     externally
    2.53
     internal
    2.12
    internal
    1.84
    Internal
    1.62
     internally
    1.47
     Internal
    1.40
    Activations Density 0.009%

    No Known Activations