© 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. 7106
    Prev
    Next
    INDEX
    Explanations

    technical terms related to business, technology, and innovation

    oai_token-act-pair · gpt-3.5-turbo

    statements about official announcements or updates

    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
     Pigs
    -0.70
     Koran
    -0.64
    udic
    -0.60
    illac
    -0.60
    hua
    -0.60
    !,
    -0.59
     Prosper
    -0.56
     bribe
    -0.55
     Saud
    -0.55
    atem
    -0.55
    POSITIVE LOGITS
     nonetheless
    0.88
    etheless
    0.88
     nevertheless
    0.84
    pmwiki
    0.82
     wondering
    0.78
     revis
    0.75
     anew
    0.71
     refreshing
    0.71
     understandably
    0.70
    ãĤ¦ãĤ¹
    0.69
    Activations Density 0.744%

    No Known Activations