© 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. 7-RES-JB
    11. 1646
    Prev
    Next
    INDEX
    Explanations

    questions related to problem-solving and actions

    oai_token-act-pair · gpt-3.5-turbo

    questions and inquiries regarding actions or steps to take in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onite
    -0.64
     CVE
    -0.63
    gged
    -0.62
    cil
    -0.60
     hatched
    -0.59
    wolves
    -0.58
     factions
    -0.56
    ces
    -0.55
     comprom
    -0.55
    oes
    -0.54
    POSITIVE LOGITS
    aples
    0.65
    Explore
    0.65
     uninterrupted
    0.63
    Pause
    0.59
     Shopping
    0.59
    abases
    0.57
    interrupted
    0.56
     Activities
    0.56
     shopping
    0.56
    intensive
    0.55
    Activations Density 1.129%

    No Known Activations