© 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. 10-RES-JB
    11. 20412
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases describing actions related to movement or change in location

    oai_token-act-pair · gpt-3.5-turbo

    end punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     microbiome
    -0.78
     advis
    -0.75
    velop
    -0.72
     contraction
    -0.71
     categor
    -0.70
     satell
    -0.70
     amplification
    -0.70
     preference
    -0.69
    bledon
    -0.68
    tera
    -0.68
    POSITIVE LOGITS
     Written
    1.73
     Meanwhile
    1.64
     Along
    1.34
     Luckily
    1.32
     Eventually
    1.31
     Fortunately
    1.27
     Together
    1.26
     Unfortunately
    1.26
     Unable
    1.26
     Whilst
    1.25
    Activations Density 0.184%

    No Known Activations