© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 20917
    Prev
    Next
    INDEX
    Explanations

    words related to glucose and carbohydrate consumption and levels

    oai_token-act-pair · gpt-3.5-turbo

    terms related to glucose, carbohydrates, and reliability

    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
    unes
    -0.92
    alty
    -0.83
    opa
    -0.82
    atory
    -0.82
    unal
    -0.81
    atorial
    -0.81
    eyed
    -0.79
    abet
    -0.77
    als
    -0.77
    ovie
    -0.77
    POSITIVE LOGITS
     Hicks
    0.71
    mble
    0.70
     Resurrection
    0.69
     Trace
    0.67
     Gou
    0.67
    TPS
    0.66
    feed
    0.65
     guiActiveUnfocused
    0.65
     sqor
    0.65
    llular
    0.64
    Activations Density 0.047%

    No Known Activations