© 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. 11-RES-JB
    11. 9495
    Prev
    Next
    INDEX
    Explanations

    phrases related to being away from a particular place or group

    oai_token-act-pair · gpt-3.5-turbo

    references to being away from home or family

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.83
    çĶ°
    -0.69
    itone
    -0.68
    meal
    -0.67
    fif
    -0.65
    tek
    -0.65
    BILL
    -0.64
    ©¶æ¥µ
    -0.64
    unn
    -0.64
    PDF
    -0.63
    POSITIVE LOGITS
     home
    1.04
     civilization
    1.03
     civilisation
    0.97
     afar
    0.92
     reality
    0.91
     whence
    0.85
     danger
    0.84
     shore
    0.84
     contention
    0.78
     norm
    0.78
    Activations Density 0.151%

    No Known Activations