© 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. 6-RES-JB
    11. 7896
    Prev
    Next
    INDEX
    Explanations

    information related to statistical margins of error

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating statistical margins of error

    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
    wives
    -0.84
    è¦ļéĨĴ
    -0.81
     Reloaded
    -0.77
    wife
    -0.74
    orer
    -0.74
    soDeliveryDate
    -0.72
    xual
    -0.68
    itions
    -0.68
    heid
    -0.68
    marked
    -0.66
    POSITIVE LOGITS
     maturity
    0.83
     parity
    0.78
     separation
    0.76
     accomplishment
    0.75
     computation
    0.74
     disbelief
    0.72
     communication
    0.71
     contention
    0.71
     competence
    0.70
     gain
    0.68
    Activations Density 0.108%

    No Known Activations