© 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. 20662
    Prev
    Next
    INDEX
    Explanations

    terms related to completeness or abundance

    oai_token-act-pair · gpt-3.5-turbo

    words related to repeating patterns, particularly in an athletic or performance context

    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
     deposit
    -0.77
     narrower
    -0.72
     intervening
    -0.68
    election
    -0.65
    dim
    -0.63
    period
    -0.63
    rha
    -0.62
    ether
    -0.62
    circ
    -0.62
    ascus
    -0.62
    POSITIVE LOGITS
    lete
    1.55
    letes
    1.02
    ONSORED
    0.80
    agues
    0.79
    lihood
    0.77
    lli
    0.76
    ttes
    0.73
    tsky
    0.72
    llo
    0.72
     Crusade
    0.71
    Activations Density 0.005%

    No Known Activations