© 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. 6410
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data, such as numbers and coding symbols

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to estimates and time frames

    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
    intent
    -0.83
    idas
    -0.68
    æł
    -0.66
    represented
    -0.65
     Specifically
    -0.63
    reetings
    -0.63
    represent
    -0.63
    aucas
    -0.62
    omorphic
    -0.60
    æ©Ł
    -0.60
    POSITIVE LOGITS
     eventually
    0.76
     Eventually
    0.66
     hindsight
    0.64
     relapse
    0.63
     restart
    0.63
    Eventually
    0.62
     reopen
    0.62
     Notting
    0.61
     historians
    0.61
     discouraged
    0.60
    Activations Density 1.916%

    No Known Activations