© 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. 1-RES-JB
    11. 8045
    Prev
    Next
    INDEX
    Explanations

    mentions of "everyday" or common occurrences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to daily life experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aternal
    -0.70
    Naz
    -0.69
    ripp
    -0.66
    zik
    -0.66
    eded
    -0.63
    GRE
    -0.63
    essee
    -0.62
    owitz
    -0.62
    kers
    -0.62
    phabet
    -0.62
    POSITIVE LOGITS
     everyday
    1.26
     Everyday
    1.02
    etheless
    0.88
     lapt
    0.80
     encount
    0.80
     ingred
    0.77
     necessities
    0.74
    ãĥīãĥ©ãĤ´ãĥ³
    0.74
     experien
    0.73
    £ı
    0.73
    Activations Density 0.004%

    No Known Activations