© 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. 9-RES-JB
    11. 21173
    Prev
    Next
    INDEX
    Explanations

    phrases related to temperature and physical sensations

    oai_token-act-pair · gpt-3.5-turbo

    references to conditions or states of being that may change or cease to exist

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     theirs
    -0.71
     THEM
    -0.65
     thereof
    -0.64
     Them
    -0.62
    them
    -0.62
     them
    -0.60
     They
    -0.58
    They
    -0.55
     they
    -0.53
    they
    -0.53
    POSITIVE LOGITS
    cffffcc
    0.67
    alyses
    0.66
    ©¶æ
    0.65
    arcer
    0.65
    ãĤ´ãĥ³
    0.63
    orney
    0.61
    externalActionCode
    0.59
    GoldMagikarp
    0.58
    nyder
    0.58
    ractions
    0.58
    Activations Density 1.258%

    No Known Activations