© 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. 8107
    Prev
    Next
    INDEX
    Explanations

    superlatives representing the largest or most extreme degree of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "gest" or its variations

    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
     AUTHOR
    -0.70
     accompanied
    -0.63
     entitled
    -0.62
    oo
    -0.60
     patriotism
    -0.58
     Lovely
    -0.57
     compiled
    -0.57
     somehow
    -0.57
     Ruk
    -0.56
     governed
    -0.56
    POSITIVE LOGITS
    gest
    4.65
     gest
    1.49
     Gest
    1.43
    ges
    1.40
    ger
    1.38
    ging
    1.31
    est
    1.30
    liest
    1.24
    gers
    1.23
    gie
    1.19
    Activations Density 0.005%

    No Known Activations