© 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. 17791
    Prev
    Next
    INDEX
    Explanations

    phrases related to exhibitions or displays

    oai_token-act-pair · gpt-3.5-turbo

    mentions of performances or presentations, particularly in the context of events or exhibitions

    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
    tymology
    -0.71
     notor
    -0.65
    illet
    -0.64
    etheless
    -0.63
     calcul
    -0.62
     srf
    -0.61
    retch
    -0.59
     solitary
    -0.59
     captcha
    -0.59
     cement
    -0.57
    POSITIVE LOGITS
    biz
    1.55
    manship
    1.38
    case
    1.28
    alter
    1.26
    downs
    1.22
    cases
    1.19
    room
    1.19
    rooms
    1.19
    boat
    1.11
    runners
    1.09
    Activations Density 0.051%

    No Known Activations