© 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. 7-RES-JB
    11. 2748
    Prev
    Next
    INDEX
    Explanations

    bright and positive words or concepts

    oai_token-act-pair · gpt-3.5-turbo

    frequent usage of the word "bright"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilage
    -0.75
    utor
    -0.71
    trl
    -0.68
    GAN
    -0.67
    Accessory
    -0.66
    berus
    -0.66
    undle
    -0.64
    uberty
    -0.63
    obic
    -0.63
    sbm
    -0.63
    POSITIVE LOGITS
    ening
    1.37
    ened
    1.28
    eners
    1.18
    ener
    1.08
     lights
    1.00
    eyed
    0.96
     eyed
    0.92
    enment
    0.91
    lights
    0.89
     bulb
    0.88
    Activations Density 0.026%

    No Known Activations