© 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. 4-RES-JB
    11. 1955
    Prev
    Next
    INDEX
    Explanations

    proper nouns such as names of places or organizations

    oai_token-act-pair · gpt-3.5-turbo

    key entities, organizations, and significant issues 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
    anwhile
    -0.72
    çĶ°
    -0.64
    cffffcc
    -0.63
    undai
    -0.60
    ĪĴ
    -0.57
    quished
    -0.55
     Tradable
    -0.55
    00200000
    -0.52
    .).
    -0.52
    \.
    -0.52
    POSITIVE LOGITS
     weddings
    0.53
     outweigh
    0.50
    versive
    0.49
     grammar
    0.49
    Reviewer
    0.49
     Fitz
    0.48
     viz
    0.44
     perceived
    0.44
     hindsight
    0.44
     architecture
    0.43
    Activations Density 2.790%

    No Known Activations