© 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. 20361
    Prev
    Next
    INDEX
    Explanations

    instances of the word "still" followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "still."

    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
     ratings
    -0.69
     Cups
    -0.64
     sub
    -0.63
     home
    -0.62
     cups
    -0.61
     entry
    -0.60
     module
    -0.60
     signature
    -0.58
     members
    -0.58
     Cup
    -0.58
    POSITIVE LOGITS
    still
    4.22
     still
    1.49
    now
    1.41
    Still
    1.40
    currently
    1.35
    again
    1.27
    actually
    1.24
    mostly
    1.24
     Still
    1.21
    always
    1.19
    Activations Density 0.009%

    No Known Activations