© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 4321
    Prev
    Next
    INDEX
    Explanations

    adjectives or adverbs describing ease or quickness

    oai_token-act-pair · gpt-3.5-turbo

    descriptive phrases that indicate simplicity or ease with certain situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thru
    -0.60
     uncond
    -0.55
    Dur
    -0.54
     skate
    -0.53
     outgoing
    -0.53
    deen
    -0.53
     Comprehensive
    -0.53
    thood
    -0.53
     chop
    -0.51
     OR
    -0.51
    POSITIVE LOGITS
     hypocrisy
    0.80
     fodder
    0.77
    shadow
    0.74
    spring
    0.73
     cynicism
    0.72
     Orwell
    0.72
    Evidence
    0.67
    aber
    0.67
    worn
    0.67
     echoes
    0.67
    Activations Density 0.347%

    No Known Activations