© 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. 8-RES-JB
    11. 2631
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mechanical or scientific processes and actions

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to biological processes and engineering systems

    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
    folk
    -0.82
    achu
    -0.79
     Haram
    -0.77
    official
    -0.74
    ottest
    -0.74
    soDeliveryDate
    -0.73
    Strange
    -0.69
    JR
    -0.67
    Mos
    -0.65
    izarre
    -0.65
    POSITIVE LOGITS
     syndrome
    1.17
     Syndrome
    0.93
     capability
    0.86
    metry
    0.86
     avoidance
    0.83
    ability
    0.80
     technology
    0.77
     removal
    0.77
     conversions
    0.76
     clauses
    0.76
    Activations Density 0.514%

    No Known Activations