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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 11990
    Prev
    Next
    INDEX
    Explanations

    terms related to therapeutic practices and medicinal treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to therapeutic efficacy and medicinal benefits

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    buck
    -0.80
    swick
    -0.79
    iger
    -0.77
    hers
    -0.77
    abet
    -0.76
    erity
    -0.75
    standing
    -0.74
    ership
    -0.73
    mpeg
    -0.73
    gered
    -0.72
    POSITIVE LOGITS
     Pwr
    0.98
     therapeutic
    0.87
     breakthrough
    0.85
     therape
    0.84
     interventions
    0.81
     Goods
    0.79
     intervention
    0.78
     dose
    0.75
     effic
    0.73
     significance
    0.73
    Activations Density 0.013%

    No Known Activations