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. 6-RES-JB
    6. 20772
    Prev
    Next
    INDEX
    Explanations

    the word "usually" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a common occurrence or generalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orchestra
    -0.72
     Integrity
    -0.70
     Abdullah
    -0.66
     Agenda
    -0.66
     Push
    -0.66
    chell
    -0.64
    eem
    -0.63
     Bird
    -0.62
     Feld
    -0.62
     Kob
    -0.60
    POSITIVE LOGITS
    entimes
    1.09
     overlooked
    0.87
     referred
    0.84
     consist
    0.82
     aspir
    0.79
     accomp
    0.79
     relegated
    0.78
     frowned
    0.78
     regarded
    0.77
     suspects
    0.77
    Activations Density 0.040%

    No Known Activations