© 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. 9-RES-JB
    11. 3750
    Prev
    Next
    INDEX
    Explanations

    prepositions and their combinations with other words

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĿ
    -0.73
    ICO
    -0.72
    moon
    -0.72
    ratulations
    -0.70
    rolet
    -0.70
    onica
    -0.69
    HAEL
    -0.69
    raf
    -0.68
    olo
    -0.68
    DIV
    -0.67
    POSITIVE LOGITS
     hopes
    1.17
     pursuit
    1.12
     order
    1.08
     anticipation
    1.05
     spite
    1.02
     lieu
    1.01
     ways
    1.00
     preparation
    1.00
     vain
    0.98
     accordance
    0.97
    Activations Density 0.424%

    No Known Activations