© 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. 2-RES-JB
    11. 11115
    Prev
    Next
    INDEX
    Explanations

    celebrity names, with a particular focus on the name "Venus."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Venus" along with related names or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oley
    -0.78
    UFF
    -0.74
    REC
    -0.73
     behav
    -0.72
    alach
    -0.71
    ulton
    -0.71
    owler
    -0.68
    à¨
    -0.67
    OOL
    -0.67
    ORD
    -0.67
    POSITIVE LOGITS
     Venus
    1.13
    angel
    0.79
     eclipse
    0.78
    arium
    0.77
     eclips
    0.75
     Celest
    0.75
     Luna
    0.75
     Ascend
    0.74
     Mistress
    0.74
    uous
    0.73
    Activations Density 0.011%

    No Known Activations