© 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. 7-RES-JB
    11. 23780
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and body parts, particularly focusing on heart-related issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to health issues and risks involving body parts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¤ãĥĪ
    -0.93
    Reward
    -0.84
    ebted
    -0.83
    quished
    -0.78
     Savings
    -0.77
    inational
    -0.76
     Intervention
    -0.75
    isoft
    -0.74
     Tradable
    -0.74
    aution
    -0.74
    POSITIVE LOGITS
     thighs
    1.19
     necks
    1.18
     torso
    1.14
     shoulders
    1.14
     legs
    1.13
     limbs
    1.11
     neck
    1.10
     lungs
    1.09
     throat
    1.09
     palate
    1.06
    Activations Density 0.279%

    No Known Activations