© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 9220
    Prev
    Next
    INDEX
    Explanations

    mentions of friendships or friendly interactions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of friendship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tarians
    -0.69
    aeda
    -0.65
    ournal
    -0.62
    Analysis
    -0.61
     untreated
    -0.61
     chloride
    -0.59
    acent
    -0.58
    ERO
    -0.57
     heel
    -0.57
    ilion
    -0.55
    POSITIVE LOGITS
    liest
    1.67
    liness
    1.66
    lier
    1.66
    lies
    1.53
    ship
    1.21
    ships
    1.18
    finder
    0.92
    hips
    0.88
    hetical
    0.84
    nee
    0.83
    Activations Density 0.040%

    No Known Activations