© 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. 2822
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles used in various contexts

    oai_token-act-pair · gpt-3.5-turbo
    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
    illions
    -0.78
    anasia
    -0.75
    advertising
    -0.70
    redibly
    -0.70
    iest
    -0.70
    ģĸ
    -0.68
    htaking
    -0.68
    largest
    -0.68
    nea
    -0.66
    isine
    -0.66
    POSITIVE LOGITS
     upcoming
    0.90
     later
    0.86
     other
    0.85
     different
    0.83
     newer
    0.82
     various
    0.80
     recent
    0.78
     elsewhere
    0.78
     previous
    0.77
     subsequent
    0.76
    Activations Density 0.754%

    No Known Activations