© 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. 6391
    Prev
    Next
    INDEX
    Explanations

    phrases related to importance or necessity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating critical actions or functions

    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
    DragonMagazine
    -1.00
     borrowed
    -0.74
     sprayed
    -0.69
    Cass
    -0.63
    imilar
    -0.63
    Written
    -0.62
     hairs
    -0.62
    Flor
    -0.61
    NJ
    -0.61
    balls
    -0.61
    POSITIVE LOGITS
     determining
    1.13
     ensuring
    1.08
     maintaining
    1.02
     preserving
    1.02
     achieving
    1.01
     sustaining
    1.00
     unlocking
    1.00
     understanding
    0.98
     solving
    0.96
     constructing
    0.94
    Activations Density 0.169%

    No Known Activations