© 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. 5642
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols such as fractions and mathematical terms

    oai_token-act-pair · gpt-3.5-turbo

    empty sequences or markers indicating the absence of content

    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
     realise
    -0.69
    SPONSORED
    -0.66
     directs
    -0.65
     âĢº
    -0.64
    irtual
    -0.62
     owing
    -0.61
     regardless
    -0.60
    eno
    -0.60
     partake
    -0.60
    ounces
    -0.60
    POSITIVE LOGITS
    oret
    1.68
    resa
    1.34
    atre
    1.33
    ories
    1.23
    odore
    1.16
    ory
    1.13
    ater
    1.09
    orem
    1.01
     biggest
    0.99
     earliest
    0.96
    Activations Density 0.108%

    No Known Activations