© 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. 23918
    Prev
    Next
    INDEX
    Explanations

    words related to being alone or individual solitude

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "oner," implying a focus on certain character types or attributes related to individuals

    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
    Ward
    -0.70
    Ka
    -0.68
    MAP
    -0.68
    eq
    -0.65
    ERA
    -0.65
    Seattle
    -0.64
    sheet
    -0.64
    å°Ĩ
    -0.64
    tnc
    -0.63
     Baldwin
    -0.62
    POSITIVE LOGITS
    oner
    1.40
     confir
    1.02
    getic
    0.87
     extraord
    0.82
    \\\\
    0.76
     occas
    0.75
    izabeth
    0.75
     forfeit
    0.75
     unden
    0.74
    velength
    0.73
    Activations Density 0.007%

    No Known Activations