© 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. 15671
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "This" followed by specific details or actions

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing personal opinions or views

    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
    Solution
    -0.76
    )].
    -0.68
     Solution
    -0.61
     DISTRICT
    -0.58
     Implementation
    -0.58
     multiplier
    -0.57
    BER
    -0.55
    stadt
    -0.55
     Answer
    -0.55
     GOODMAN
    -0.55
    POSITIVE LOGITS
     biography
    1.06
    His
    1.05
     his
    1.04
    his
    0.89
    Born
    0.87
     accol
    0.86
     endorsements
    0.82
     tattoos
    0.81
     autobi
    0.81
     stint
    0.80
    Activations Density 0.939%

    No Known Activations