© 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. 8-RES-JB
    11. 17785
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating size or scale

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to significant quantities or sizes

    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
    ysc
    -0.74
    uay
    -0.74
     Origins
    -0.72
    rick
    -0.72
    flies
    -0.67
    np
    -0.67
     Scully
    -0.64
     Pigs
    -0.64
     Annotations
    -0.63
     Blocks
    -0.63
    POSITIVE LOGITS
     thing
    1.18
     scenario
    0.96
     delicate
    0.93
     sensitive
    0.92
     huge
    0.90
     feat
    0.89
     drastic
    0.88
     situation
    0.88
     diverse
    0.83
     complicated
    0.83
    Activations Density 0.031%

    No Known Activations