© 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. 22582
    Prev
    Next
    INDEX
    Explanations

    dates and time-related terms

    oai_token-act-pair · gpt-3.5-turbo

    temporal indicators or references to recent events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    geries
    -0.82
    abiding
    -0.69
    Uh
    -0.66
    Maker
    -0.61
     consequential
    -0.61
    onz
    -0.61
    AND
    -0.60
    SpaceEngineers
    -0.60
    bryce
    -0.58
     Alchemy
    -0.58
    POSITIVE LOGITS
     undertook
    1.01
     launched
    0.98
     embarked
    0.96
     underwent
    0.96
     withdrew
    0.94
     announced
    0.93
     apologized
    0.93
     boasted
    0.91
     flew
    0.90
     reaff
    0.90
    Activations Density 0.168%

    No Known Activations