© 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. 4317
    Prev
    Next
    INDEX
    Explanations

    warning messages in text

    oai_token-act-pair · gpt-3.5-turbo

    warnings or notifications regarding inappropriate or graphic content

    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
     inertia
    -0.79
    --+
    -0.74
     Recovery
    -0.73
     staggered
    -0.72
    buck
    -0.71
     retire
    -0.69
     waiting
    -0.69
    town
    -0.68
     swoop
    -0.68
     patiently
    -0.66
    POSITIVE LOGITS
     pornographic
    1.63
     nudity
    1.58
     objectionable
    1.37
     depictions
    1.33
     depicting
    1.32
     satire
    1.30
     derogatory
    1.26
     lewd
    1.25
     misogyn
    1.24
     blasp
    1.22
    Activations Density 0.530%

    No Known Activations