© 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. 21657
    Prev
    Next
    INDEX
    Explanations

    terms related to technical discussions and business contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to age and generational changes

    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
     relentlessly
    -0.72
    ixty
    -0.70
     ninety
    -0.70
    every
    -0.69
     seventy
    -0.67
    irteen
    -0.66
    ãĥ©ãĥ³
    -0.65
     merciless
    -0.64
     Twice
    -0.63
     blister
    -0.63
    POSITIVE LOGITS
     etc
    1.10
     secondly
    0.96
     hopefully
    0.89
    Secondly
    0.83
     possibly
    0.82
     additionally
    0.81
     Secondly
    0.80
     ect
    0.80
     Lastly
    0.79
     maybe
    0.79
    Activations Density 1.017%

    No Known Activations