© 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. 2-RES-JB
    11. 14670
    Prev
    Next
    INDEX
    Explanations

    words related to editing or removing content, particularly in the context of information or data

    oai_token-act-pair · gpt-3.5-turbo

    words associated with editing, censoring, or filtering information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entric
    -0.79
    izoph
    -0.77
    CG
    -0.74
    Hung
    -0.69
    iber
    -0.67
    RT
    -0.67
    rones
    -0.66
     Sons
    -0.66
    gram
    -0.66
    anza
    -0.65
    POSITIVE LOGITS
     scrub
    1.21
     blob
    0.94
     mole
    0.76
     redacted
    0.76
     clearing
    0.76
    76561
    0.73
    imaru
    0.72
     fingerprints
    0.72
     shading
    0.71
    bara
    0.71
    Activations Density 0.018%

    No Known Activations