© 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. 4-RES-JB
    11. 4876
    Prev
    Next
    INDEX
    Explanations

    names or words starting with "Sande"

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'e' in various contexts

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

    No Comments

    Negative Logits
     sidx
    -0.74
    iets
    -0.74
    ategory
    -0.74
     glim
    -0.71
    anova
    -0.71
    utterstock
    -0.71
    mallow
    -0.69
     sqor
    -0.67
    irtual
    -0.67
    */(
    -0.66
    POSITIVE LOGITS
    lements
    1.39
    gger
    1.11
    zza
    1.05
    cker
    1.04
    agle
    1.03
    ld
    1.02
    gypt
    1.02
    gging
    1.00
    lev
    0.99
    cki
    0.98
    Activations Density 0.035%

    No Known Activations