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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9653
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of proximity or presence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "nowhere" and its variations, indicating a focus on lack of presence or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ULT
    -0.74
    CVE
    -0.71
    ivation
    -0.65
     Reef
    -0.62
    ilt
    -0.61
    tein
    -0.59
    tl
    -0.58
    isations
    -0.57
    FA
    -0.57
    ultural
    -0.57
    POSITIVE LOGITS
     else
    1.21
    Else
    0.97
     Else
    0.95
    xus
    0.91
    upon
    0.85
    ¿½
    0.78
    abouts
    0.75
    else
    0.75
    ĸļ
    0.74
    ĪĴ
    0.71
    Activations Density 0.017%

    No Known Activations