© 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. 8-RES-JB
    11. 2530
    Prev
    Next
    INDEX
    Explanations

    personal relationships or interactions between individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ult
    -0.77
     Turing
    -0.76
    DoS
    -0.76
    RFC
    -0.75
    ãĥĵ
    -0.74
    hack
    -0.73
    Forge
    -0.71
    Chain
    -0.71
    ãĥķãĤ©
    -0.71
    Scale
    -0.70
    POSITIVE LOGITS
     woman
    1.21
     girl
    1.19
     daughter
    1.13
     Females
    1.13
     female
    1.07
     females
    1.06
     wife
    1.04
     lady
    1.03
     person
    1.03
     women
    1.03
    Activations Density 0.474%

    No Known Activations