© 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. 2125
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific organizations and standards

    oai_token-act-pair · gpt-3.5-turbo

    references to government organizations and oversight bodies

    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
    Äĩ
    -0.82
    deck
    -0.73
    paralle
    -0.70
    flows
    -0.65
    rez
    -0.65
    canon
    -0.63
    drive
    -0.63
    ãĢı
    -0.62
    comed
    -0.62
    ãĤ¯
    -0.62
    POSITIVE LOGITS
     Institute
    1.10
     Association
    1.10
     Authority
    1.08
     Accountability
    1.07
     Commission
    1.07
     Initiative
    1.01
     Society
    1.01
     Agency
    0.99
     Board
    0.97
     Assistance
    0.96
    Activations Density 0.185%

    No Known Activations