© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 15697
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing or seeking information

    oai_token-act-pair · gpt-3.5-turbo

    references to information and details being shared or withheld

    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
     Balanced
    -0.68
    emale
    -0.66
    rican
    -0.65
    ortunately
    -0.63
    Zone
    -0.62
     Cancel
    -0.61
    xtap
    -0.58
    die
    -0.58
     aisle
    -0.57
     Carbuncle
    -0.57
    POSITIVE LOGITS
     regarding
    1.39
     concerning
    1.22
     about
    1.20
     detailing
    1.16
     pertaining
    1.13
     relating
    1.12
     confirming
    0.99
     glean
    0.98
     outlining
    0.96
    about
    0.95
    Activations Density 0.200%

    No Known Activations