© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 7722
    Prev
    Next
    INDEX
    Explanations

    questions that start with the word "Should" followed by a subject and a verb

    oai_token-act-pair · gpt-3.5-turbo

    questions that introduce topics requiring consideration or debate

    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
     Trails
    -0.68
    natureconservancy
    -0.65
     Puzzle
    -0.60
    OTOS
    -0.60
     ì
    -0.60
    ãĥīãĥ©
    -0.59
    ãĥŃ
    -0.57
     Viet
    -0.56
     Mé
    -0.56
    ITED
    -0.56
    POSITIVE LOGITS
    ering
    0.95
    ered
    0.94
    n
    0.91
    ĪĴ
    0.84
    edi
    0.76
    nt
    0.74
    not
    0.73
    acus
    0.72
     be
    0.72
    probably
    0.72
    Activations Density 0.014%

    No Known Activations