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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2-RES-JB
    11. 13057
    Prev
    Next
    INDEX
    Explanations

    mentions of sponsors or co-sponsors in texts

    oai_token-act-pair · gpt-3.5-turbo

    references to sponsorships and sponsors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pebble
    -0.73
     PCB
    -0.72
     Barclays
    -0.71
     circuit
    -0.66
     grip
    -0.65
     shareholder
    -0.64
     Aberdeen
    -0.63
     paddle
    -0.61
     draw
    -0.61
     ACTION
    -0.60
    POSITIVE LOGITS
    orship
    1.42
    orial
    1.25
    ories
    1.13
    rum
    1.12
    ured
    1.12
    urers
    1.12
    or
    1.10
    uring
    1.08
    ures
    1.07
    urations
    1.06
    Activations Density 0.026%

    No Known Activations