© 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. 2104
    Prev
    Next
    INDEX
    Explanations

    references to supporters or groups of people supporting a cause

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups that support a person, cause, or movement

    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
     geological
    -0.66
    PASS
    -0.65
    ered
    -0.64
    abus
    -0.62
    geon
    -0.61
    DERR
    -0.61
     situational
    -0.61
     ILCS
    -0.60
    intestinal
    -0.60
    pmwiki
    -0.60
    POSITIVE LOGITS
    hesis
    1.00
    hetical
    0.97
    hips
    0.83
    Supporters
    0.79
    hip
    0.78
     supporters
    0.77
    heses
    0.75
     Supporters
    0.75
     cheering
    0.73
    leader
    0.72
    Activations Density 0.023%

    No Known Activations