© 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. 2-RES-JB
    11. 803
    Prev
    Next
    INDEX
    Explanations

    the word segment "iat" within different contexts

    oai_token-act-pair · gpt-4-turbo

    words related to the Asian community

    oai_token-act-pair · gpt-3.5-turbo

    the suffix "iat" in various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tnc
    -0.68
    Snow
    -0.67
     Angry
    -0.66
    âĵĺ
    -0.64
    FTWARE
    -0.63
    CVE
    -0.63
    CONCLUS
    -0.62
     Gale
    -0.61
    perty
    -0.61
    party
    -0.61
    POSITIVE LOGITS
    rix
    1.04
    iat
    1.01
    ypes
    0.94
    ossal
    0.90
    oreal
    0.90
    iaz
    0.84
    oga
    0.82
    anamo
    0.82
    terness
    0.82
    unia
    0.81
    Activations Density 0.013%

    No Known Activations