© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5512
    Prev
    Next
    INDEX
    Explanations

    unique special characters

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that indicate significant numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alexa
    -0.71
     redes
    -0.68
    etta
    -0.65
     Taken
    -0.61
     Esper
    -0.61
     XIII
    -0.59
    isd
    -0.59
     effort
    -0.59
     endeavour
    -0.58
     Conf
    -0.57
    POSITIVE LOGITS
    à¼
    0.93
    interrupted
    0.92
    IBLE
    0.87
    ?????-?????-
    0.86
    Wait
    0.85
    WARNING
    0.80
    Oracle
    0.79
    BUT
    0.78
    WAR
    0.76
    Anyway
    0.73
    Activations Density 0.100%

    No Known Activations