© 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. 8-RES-JB
    11. 4597
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transact
    -0.75
     consolidation
    -0.74
     sequential
    -0.73
     closet
    -0.71
     fermented
    -0.71
     peanuts
    -0.71
     transition
    -0.70
     mattress
    -0.69
     conglomer
    -0.68
     absorption
    -0.67
    POSITIVE LOGITS
     Moreover
    1.15
     However
    1.13
     Furthermore
    1.11
     Therefore
    1.07
     Similarly
    1.07
     Asked
    1.07
     Conversely
    1.05
     But
    1.05
     Though
    1.03
     Nonetheless
    1.03
    Activations Density 0.171%

    No Known Activations