© 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. 18740
    Prev
    Next
    INDEX
    Explanations

    references to the brand "Nest"

    oai_token-act-pair · gpt-3.5-turbo

    references to the brand "Nest" and its related concepts

    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
    WAYS
    -0.74
    fare
    -0.71
    ा
    -0.68
    ++++++++++++++++
    -0.66
    idents
    -0.62
    Thumbnail
    -0.61
    VERSION
    -0.61
    primary
    -0.60
    ×ķ
    -0.60
    Primary
    -0.60
    POSITIVE LOGITS
    lé
    1.32
    ea
    1.05
    thal
    0.93
    hetically
    0.93
    led
    0.88
    lund
    0.87
    orius
    0.84
    otle
    0.84
    rone
    0.83
    eers
    0.83
    Activations Density 0.043%

    No Known Activations