© 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. 14160
    Prev
    Next
    INDEX
    Explanations

    terms related to importance, value, or impact

    oai_token-act-pair · gpt-3.5-turbo

    sentences that mark a conclusion or summary

    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
     reversible
    -0.79
     nons
    -0.75
     allowances
    -0.74
     allowance
    -0.73
     involuntary
    -0.72
     unspecified
    -0.72
     glim
    -0.71
     emanc
    -0.70
     handc
    -0.69
     implied
    -0.67
    POSITIVE LOGITS
     However
    1.51
     Yet
    1.46
     Its
    1.43
     Recently
    1.39
     Unfortunately
    1.37
     Nevertheless
    1.36
     But
    1.33
     Moreover
    1.33
     Besides
    1.32
     Sadly
    1.32
    Activations Density 0.545%

    No Known Activations