© 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. 3-RES-JB
    11. 6021
    Prev
    Next
    INDEX
    Explanations

    terms related to challenging or confronting situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to contradictions or ambiguous situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NCT
    -0.95
     Attribution
    -0.71
     Gutenberg
    -0.69
     CoC
    -0.69
     Cong
    -0.66
    é¾
    -0.65
     shroud
    -0.62
    æѦ
    -0.62
     Hole
    -0.61
     Comfort
    -0.61
    POSITIVE LOGITS
    entin
    0.90
    eworld
    0.86
    ratulations
    0.85
    arate
    0.81
    onymous
    0.77
    adr
    0.77
    ochet
    0.77
    unin
    0.76
    otine
    0.76
    avage
    0.76
    Activations Density 0.041%

    No Known Activations