© 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. 18095
    Prev
    Next
    INDEX
    Explanations

    common phrases or specific patterns that are repeated throughout the text

    oai_token-act-pair · gpt-3.5-turbo

    references to synchronization or simultaneous 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
    ayed
    -0.39
    agram
    -0.37
    ciation
    -0.36
    arius
    -0.35
    ona
    -0.35
     Cosponsors
    -0.34
    alysed
    -0.33
     collided
    -0.32
    rika
    -0.32
    aki
    -0.32
    POSITIVE LOGITS
     Pod
    0.34
     âĢİ
    0.33
     Chance
    0.31
     cle
    0.30
     Homeland
    0.30
     Dyn
    0.30
     Throne
    0.29
     un
    0.28
     Unt
    0.28
     Clip
    0.27
    Activations Density 4.768%

    No Known Activations