© 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. 23576
    Prev
    Next
    INDEX
    Explanations

    the word "vast"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "vast."

    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
    ople
    -0.80
    SHIP
    -0.78
    WAR
    -0.75
    PT
    -0.71
    Dialogue
    -0.70
    CP
    -0.66
    headers
    -0.64
    alias
    -0.63
    gged
    -0.62
    ishops
    -0.62
    POSITIVE LOGITS
     majority
    1.07
     vast
    0.91
     amounts
    0.91
     expans
    0.86
     swat
    0.82
     disproportion
    0.81
     tracts
    0.80
    itud
    0.79
     gulf
    0.78
     quantities
    0.76
    Activations Density 0.010%

    No Known Activations