© 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. 2503
    Prev
    Next
    INDEX
    Explanations

    mentions of critics or criticisms

    oai_token-act-pair · gpt-3.5-turbo

    references to critics and critical commentary

    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
     Anniversary
    -0.83
     Pradesh
    -0.68
    uras
    -0.65
    owship
    -0.63
     Civilization
    -0.61
     Foods
    -0.60
     +/-
    -0.60
     Adventures
    -0.60
    OTUS
    -0.59
     manslaughter
    -0.59
    POSITIVE LOGITS
    paces
    0.96
    hesis
    0.96
    hip
    0.92
     accuse
    0.86
    ervatives
    0.85
    hetical
    0.82
     critics
    0.81
    sbm
    0.80
     allege
    0.80
    heses
    0.79
    Activations Density 0.056%

    No Known Activations