Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22982
    Prev
    Next
    INDEX
    Explanations

    academic titles and names with specific characteristics

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to individuals or research subjects

    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
     Craigslist
    -0.75
     Vanity
    -0.71
     Oath
    -0.68
    aepernick
    -0.68
    Offline
    -0.68
     Daddy
    -0.67
     TRUMP
    -0.67
     Celebration
    -0.66
     Exile
    -0.66
    VERTISEMENT
    -0.65
    POSITIVE LOGITS
     hypothes
    1.34
     hypothesized
    1.26
     et
    1.20
     resear
    1.20
     studied
    1.19
     analysed
    1.16
     calculates
    1.08
     researchers
    1.07
     explains
    1.07
     suggests
    1.07
    Activations Density 0.212%

    No Known Activations