© 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. 0-RES-JB
    11. 20562
    Prev
    Next
    INDEX
    Explanations

    phrases related to charitable or benevolent organizations and movements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gaming or competitive events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASHINGTON
    -0.68
     erase
    -0.67
     coping
    -0.66
    umb
    -0.64
     sleepy
    -0.64
     paralle
    -0.63
     tracks
    -0.63
     cope
    -0.62
    iko
    -0.62
    ALTH
    -0.61
    POSITIVE LOGITS
     Offensive
    2.87
     Defensive
    2.75
     Shield
    1.47
     Supporting
    1.23
     Melee
    1.06
     Racial
    1.04
     Known
    1.01
     Penal
    0.99
     Attacks
    0.98
     Rookie
    0.97
    Activations Density 0.036%

    No Known Activations