© 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. 7-RES-JB
    11. 20048
    Prev
    Next
    INDEX
    Explanations

    instances of the contraction "it's" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the ending letter "s" in singular or possessive form at the end of words

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prior
    -0.64
     Guant
    -0.60
     Continental
    -0.59
    Prior
    -0.56
     Gaul
    -0.56
     Brune
    -0.56
     Rothschild
    -0.55
     Tours
    -0.55
    MAP
    -0.55
     Bagg
    -0.54
    POSITIVE LOGITS
     raining
    0.92
     gonna
    0.83
    orno
    0.82
    leeve
    0.82
     imperative
    0.79
     impossible
    0.79
     advisable
    0.78
     worth
    0.77
     abundantly
    0.76
     unclear
    0.75
    Activations Density 0.095%

    No Known Activations