© 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. 3235
    Prev
    Next
    INDEX
    Explanations

    words related to technology and processes

    oai_token-act-pair · gpt-3.5-turbo

    recurring themes or patterns related to technology, memes, and cultural trends

    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
    ayne
    -0.74
    anship
    -0.73
    ew
    -0.71
    uador
    -0.70
    estern
    -0.65
    orest
    -0.65
    uin
    -0.64
    olid
    -0.64
    OTH
    -0.64
    enium
    -0.63
    POSITIVE LOGITS
    iosyncr
    0.84
     suffers
    0.71
     relies
    0.68
     evolves
    0.67
     esche
    0.66
     disclaim
    0.65
     bear
    0.65
     subjective
    0.65
     opio
    0.64
     bears
    0.62
    Activations Density 0.199%

    No Known Activations