© 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. 4-RES-JB
    11. 544
    Prev
    Next
    INDEX
    Explanations

    female family members and their relationships to other individuals involved in a situation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to familial relationships

    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
    hower
    -0.77
    ahime
    -0.71
     Detected
    -0.66
     Era
    -0.66
     Carbuncle
    -0.66
     1933
    -0.64
     Keynes
    -0.63
     pand
    -0.63
    punk
    -0.63
     Throne
    -0.62
    POSITIVE LOGITS
     testified
    0.85
     allege
    0.79
    ributes
    0.79
     testim
    0.77
     plead
    0.76
     mourn
    0.75
     alleges
    0.74
     remorse
    0.73
     interven
    0.73
    hetical
    0.72
    Activations Density 0.119%

    No Known Activations