© 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. 6119
    Prev
    Next
    INDEX
    Explanations

    words related to tall structures such as skyscrapers

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns related to architecture and culinary items

    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
     gloom
    -0.71
     Grip
    -0.65
     constellation
    -0.65
     Vlad
    -0.65
     Doctrine
    -0.65
     Feast
    -0.64
     complicity
    -0.64
     positional
    -0.64
     tune
    -0.63
     striking
    -0.62
    POSITIVE LOGITS
    orial
    1.13
    etime
    1.12
    ew
    1.05
    ement
    1.04
    eed
    1.03
    ere
    1.01
    raph
    1.01
    ewater
    1.01
    ez
    1.00
    estate
    0.98
    Activations Density 0.119%

    No Known Activations