© 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. 6234
    Prev
    Next
    INDEX
    Explanations

    website URLs containing the word "forge"

    oai_token-act-pair · gpt-3.5-turbo

    URLs or website links

    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
    racial
    -0.57
    etheless
    -0.57
    soType
    -0.56
    aucas
    -0.54
     privacy
    -0.54
     Privacy
    -0.53
    phrine
    -0.52
    xual
    -0.51
    opian
    -0.51
    leans
    -0.51
    POSITIVE LOGITS
    reau
    0.64
    odder
    0.60
     Ferry
    0.60
    udo
    0.55
    ÃĥÃĤ
    0.53
     guiIcon
    0.53
     modem
    0.53
     locom
    0.52
     overhead
    0.51
    axe
    0.51
    Activations Density 1.369%

    No Known Activations