© 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. 11-RES-JB
    11. 10069
    Prev
    Next
    INDEX
    Explanations

    abbreviations related to air pollution

    oai_token-act-pair · gpt-3.5-turbo

    references to particulate matter measurements in the air quality context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ttes
    -0.86
    come
    -0.86
    inese
    -0.74
    kowski
    -0.66
    neys
    -0.65
    combe
    -0.65
    hered
    -0.63
    cha
    -0.63
    seeing
    -0.62
    cko
    -0.61
    POSITIVE LOGITS
    NH
    1.21
    AZ
    1.14
    OUNT
    1.10
    Cs
    1.08
    essage
    1.05
    MU
    0.99
    AX
    0.97
    PK
    0.97
    Vs
    0.94
    OVA
    0.94
    Activations Density 0.037%

    No Known Activations