© 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 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. 10-RES-JB
    11. 6257
    Prev
    Next
    INDEX
    Explanations

    words related to injuries and medical conditions that require attention

    oai_token-act-pair · gpt-3.5-turbo

    terms related to individuals who are harmed or impacted by various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orously
    -0.78
    guided
    -0.74
    nown
    -0.74
    resent
    -0.71
    ledge
    -0.71
    kill
    -0.70
    pun
    -0.69
    antine
    -0.66
    tesy
    -0.66
    Gate
    -0.66
    POSITIVE LOGITS
     persons
    1.28
     individuals
    1.26
     Persons
    0.98
     parties
    0.97
     comrades
    0.96
     youths
    0.94
     relatives
    0.92
     brethren
    0.91
     spouses
    0.89
     Individuals
    0.89
    Activations Density 0.192%

    No Known Activations