© 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. 4-RES-JB
    11. 9663
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenges, difficulties, and obstacles

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating challenges, struggles, or unresolved issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llor
    -0.80
    lect
    -0.75
    inking
    -0.73
    atra
    -0.72
    ingle
    -0.70
    umo
    -0.70
    istant
    -0.69
    oru
    -0.68
    vertisement
    -0.68
    imity
    -0.67
    POSITIVE LOGITS
     hurdles
    0.73
    BLE
    0.69
    RESULTS
    0.68
    éĽ
    0.68
    ANCE
    0.68
    kees
    0.67
    Hig
    0.66
    soDeliveryDate
    0.66
    antics
    0.66
     Rebels
    0.65
    Activations Density 0.047%

    No Known Activations