© 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. 16753
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts between different subjects or objects

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to size comparisons and measurements

    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
     Grateful
    -0.58
     Ruby
    -0.50
     Stard
    -0.50
     Transcript
    -0.49
     Franks
    -0.49
     Ange
    -0.49
     Cummings
    -0.49
     Shea
    -0.49
     Stain
    -0.48
     Garr
    -0.47
    POSITIVE LOGITS
    trak
    0.83
     likewise
    0.82
    arser
    0.76
     similarly
    0.71
     opposite
    0.67
     versa
    0.66
    çķ
    0.64
    è»
    0.63
    oliath
    0.62
     Same
    0.62
    Activations Density 1.769%

    No Known Activations