© 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. 16929
    Prev
    Next
    INDEX
    Explanations

    technical terms related to information retrieval

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing curiosity or inquiry

    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
    ©¶æ¥µ
    -0.72
    ©¶æ
    -0.70
     exting
    -0.66
    ĸļ士
    -0.61
    odder
    -0.60
    DeliveryDate
    -0.59
     Dillon
    -0.58
    ¥ŀ
    -0.57
    ailability
    -0.56
    HEAD
    -0.55
    POSITIVE LOGITS
    uddin
    0.68
     âĸº
    0.67
    vati
    0.64
    abeth
    0.64
    ":"
    0.64
     CPR
    0.63
    )=(
    0.62
    .............
    0.61
    _>
    0.60
    af
    0.59
    Activations Density 0.204%

    No Known Activations