© 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. 0-RES-JB
    11. 16837
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Over" in the context of comparing or counting

    oai_token-act-pair · gpt-3.5-turbo

    the word "Over" with high frequency and emphasis on its contextual usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hitherto
    -0.67
     prov
    -0.66
    pson
    -0.64
     sow
    -0.61
     pretended
    -0.60
     secondly
    -0.60
    inet
    -0.60
     conspic
    -0.60
    amine
    -0.59
     propos
    -0.59
    POSITIVE LOGITS
     Over
    3.28
    Over
    2.44
     OVER
    1.99
    over
    1.87
     Overs
    1.65
     over
    1.58
    OVER
    1.48
    overs
    1.48
     Under
    1.43
     Overt
    1.40
    Activations Density 0.006%

    No Known Activations