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. 9-RES-JB
    6. 4558
    Prev
    Next
    INDEX
    Explanations

    phrases related to exploring ideas or proposals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "the" and concepts related to proposals or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.79
    onse
    -0.75
    !
    -0.68
    !!
    -0.68
     namely
    -0.67
     according
    -0.66
    SHIP
    -0.66
    VICE
    -0.65
    Cod
    -0.65
    !.
    -0.65
    POSITIVE LOGITS
     notion
    1.64
     idea
    1.63
     possibility
    1.43
     latter
    1.31
     same
    1.25
     concept
    1.22
     virtues
    1.03
     assumption
    1.02
     mantle
    1.01
     underdog
    0.99
    Activations Density 0.455%

    No Known Activations