© 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. 6899
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming and commands

    oai_token-act-pair · gpt-3.5-turbo

    patterns related to security vulnerabilities or configurations in technology

    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
     cutting
    -0.68
     heartbreaking
    -0.66
     fortunate
    -0.65
     tink
    -0.65
     snap
    -0.62
     leaving
    -0.62
     nerv
    -0.61
     witnessing
    -0.61
     lucky
    -0.60
     tears
    -0.60
    POSITIVE LOGITS
    alist
    1.29
    edition
    1.06
    whatever
    0.99
    container
    0.98
    wrapper
    0.96
    etc
    0.93
    controller
    0.93
    generic
    0.93
    size
    0.90
    style
    0.90
    Activations Density 0.087%

    No Known Activations