© 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. 9-RES-JB
    11. 14344
    Prev
    Next
    INDEX
    Explanations

    various lists containing actionable items or tips

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to lists or collections of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulsion
    -0.72
    ensions
    -0.72
    cffffcc
    -0.70
    erity
    -0.65
    yss
    -0.64
    ictions
    -0.64
    patch
    -0.63
    Ń·
    -0.63
    status
    -0.63
    MT
    -0.63
    POSITIVE LOGITS
     Helpful
    0.75
    ottest
    0.72
    hooting
    0.68
     pertaining
    0.68
     debunk
    0.67
     beginners
    0.66
     âĢº
    0.66
     worth
    0.66
     checklist
    0.65
     Learned
    0.64
    Activations Density 0.228%

    No Known Activations