© 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. 3-RES-JB
    11. 13142
    Prev
    Next
    INDEX
    Explanations

    words related to anonymity and pseudonyms

    oai_token-act-pair · gpt-3.5-turbo

    elements related to ambiguity and classification concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ccording
    -0.69
    PDATE
    -0.66
     corrid
    -0.59
     skelet
    -0.58
     millenn
    -0.58
     exha
    -0.57
    iosyn
    -0.56
     cryst
    -0.56
     unden
    -0.56
     GOODMAN
    -0.55
    POSITIVE LOGITS
    ensis
    0.70
    phia
    0.68
    ption
    0.68
    aires
    0.68
    ulous
    0.66
    ious
    0.66
    ette
    0.65
    aten
    0.64
    esque
    0.64
    ously
    0.63
    Activations Density 1.098%

    No Known Activations