© 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. 4-RES-JB
    11. 22308
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic locations or landmarks

    oai_token-act-pair · gpt-3.5-turbo

    terms and references related to Bosnia and obsessive behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iating
    -1.03
    iations
    -0.97
    iated
    -0.91
    ions
    -0.88
    iates
    -0.85
    iate
    -0.84
    ion
    -0.77
    iants
    -0.75
     Wolver
    -0.74
    ania
    -0.73
    POSITIVE LOGITS
     versa
    0.92
    vironment
    0.91
    tesy
    0.89
    thood
    0.78
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.76
    ħĭ
    0.75
    gements
    0.74
    ĻĤ
    0.73
     restraint
    0.72
    Ô
    0.71
    Activations Density 0.045%

    No Known Activations