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. 20350
    Prev
    Next
    INDEX
    Explanations

    words related to actions or settings involving sitting down

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to informal conversations and discussions

    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
     Russo
    -0.58
    İĭ
    -0.53
     beware
    -0.53
     credits
    -0.53
     IMAGES
    -0.53
     merc
    -0.53
     facets
    -0.52
     Romero
    -0.52
     nick
    -0.52
     Kinnikuman
    -0.52
    POSITIVE LOGITS
    pee
    0.81
    pees
    0.73
    Lago
    0.67
    culosis
    0.67
    ADRA
    0.67
    Single
    0.67
    pole
    0.66
    ulhu
    0.65
    lished
    0.65
    uate
    0.64
    Activations Density 0.202%

    No Known Activations