© 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. 20046
    Prev
    Next
    INDEX
    Explanations

    instances related to software manipulation and distribution

    oai_token-act-pair · gpt-3.5-turbo

    terms related to downloading and sharing digital files

    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
     Eisenhower
    -0.80
    ĸļ
    -0.74
    interstitial
    -0.72
    HAEL
    -0.70
     Oaks
    -0.70
    Ĭ±
    -0.68
     Hitchcock
    -0.68
    ciplinary
    -0.68
     Moody
    -0.67
     Chamberlain
    -0.66
    POSITIVE LOGITS
     infringing
    1.01
     theirs
    1.00
     freely
    0.88
     copyrighted
    0.88
     infring
    0.87
     crypto
    0.86
     content
    0.85
     software
    0.82
     themselves
    0.81
     infringement
    0.77
    Activations Density 0.768%

    No Known Activations