© 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. 8-RES-JB
    11. 6413
    Prev
    Next
    INDEX
    Explanations

    references to romantic relationships

    oai_token-act-pair · gpt-3.5-turbo

    mentions of romantic themes 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
    upon
    -0.86
    Downloadha
    -0.78
    avis
    -0.78
    ulhu
    -0.73
    ldon
    -0.73
    paio
    -0.71
    veland
    -0.66
    hern
    -0.65
    aston
    -0.65
    tower
    -0.65
    POSITIVE LOGITS
    ized
    0.97
    izing
    0.96
    ties
    0.96
    istically
    0.94
    istic
    0.93
    ization
    0.88
    ism
    0.88
     comed
    0.81
    isation
    0.79
    ists
    0.78
    Activations Density 0.033%

    No Known Activations