Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7452
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty about various matters

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce conditional statements

    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
     closed
    -0.64
     earlier
    -0.64
     bill
    -0.64
     poor
    -0.63
     worse
    -0.63
     bottom
    -0.61
     close
    -0.60
     later
    -0.60
     heavy
    -0.59
     badly
    -0.59
    POSITIVE LOGITS
     Whether
    3.27
    Whether
    3.06
    whether
    2.15
     whether
    1.61
     Regardless
    1.57
    Regardless
    1.43
    Whatever
    1.41
     Whatever
    1.41
     Either
    1.26
     Whoever
    1.18
    Activations Density 0.021%

    No Known Activations