© 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. 2226
    Prev
    Next
    INDEX
    Explanations

    phrases relating to opportunities for various actions or states

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to opportunities for improvement and innovation

    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
    é¾į
    -0.74
    terday
    -0.68
     VID
    -0.65
    ledged
    -0.60
    deen
    -0.60
    jad
    -0.59
    odore
    -0.59
    uably
    -0.59
    ravis
    -0.59
     tox
    -0.58
    POSITIVE LOGITS
     purposes
    1.06
     experimentation
    0.97
     sake
    0.96
     exploration
    0.86
    spection
    0.86
     discussion
    0.81
     customization
    0.80
     advancement
    0.78
     analysis
    0.78
     correction
    0.76
    Activations Density 0.453%

    No Known Activations