© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 4775
    Prev
    Next
    INDEX
    Explanations

    social media post captions containing a URL

    oai_token-act-pair · gpt-3.5-turbo

    URLs or web links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     afore
    -0.80
     ÂŃ
    -0.71
     caring
    -0.71
     wanting
    -0.71
     accrued
    -0.69
     condensed
    -0.69
     deciding
    -0.68
     defending
    -0.67
     recovering
    -0.67
     transitioning
    -0.66
    POSITIVE LOGITS
    zx
    1.39
    zl
    1.37
    FK
    1.37
    zn
    1.36
    gz
    1.33
    dq
    1.33
    ql
    1.33
    qv
    1.33
    GY
    1.32
    OY
    1.31
    Activations Density 0.083%

    No Known Activations