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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 20343
    Prev
    Next
    INDEX
    Explanations

    references to firearms, specifically semi-automatic guns

    oai_token-act-pair · gpt-3.5-turbo

    references to semi-automatic weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rica
    -0.72
     Fas
    -0.68
     Scrib
    -0.67
     Springs
    -0.66
     Cassidy
    -0.65
     Sins
    -0.65
     WD
    -0.65
     shaping
    -0.64
     deed
    -0.64
     Piper
    -0.64
    POSITIVE LOGITS
    finals
    1.21
    final
    1.19
    circle
    1.18
    automatic
    1.13
    conscious
    1.09
    regular
    1.05
    circ
    1.04
    professional
    1.03
    legal
    1.01
    functional
    1.01
    Activations Density 0.028%

    No Known Activations