© 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. 4-RES-JB
    11. 10459
    Prev
    Next
    INDEX
    Explanations

    words related to evaluation or judgment on a scale

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "what makes" in various contexts

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

    No Comments

    Negative Logits
     scrimmage
    -0.67
    ban
    -0.67
     nurs
    -0.67
    76561
    -0.65
    thia
    -0.65
    ---------
    -0.62
     conditioning
    -0.57
     Witch
    -0.55
     Souls
    -0.55
    herry
    -0.55
    POSITIVE LOGITS
    hift
    1.13
     sure
    1.02
    berra
    0.81
    paio
    0.77
    auri
    0.76
    elling
    0.76
    ailable
    0.74
     landfall
    0.74
    paces
    0.73
    ebin
    0.73
    Activations Density 0.129%

    No Known Activations