© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 24532
    Prev
    Next
    INDEX
    Explanations

    names of individuals with the surname "Sc" and words related to conflict or aggressive actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific surnames or last names

    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
     foremost
    -0.68
    abase
    -0.67
    hower
    -0.66
    theless
    -0.66
     craving
    -0.66
     neoc
    -0.63
     faint
    -0.63
     Ramadan
    -0.62
    ndra
    -0.60
     glor
    -0.59
    POSITIVE LOGITS
    hett
    0.83
    cheon
    0.79
    arios
    0.78
    berus
    0.74
    iron
    0.72
    eta
    0.70
    actionDate
    0.69
    driver
    0.69
    uli
    0.68
    ohm
    0.68
    Activations Density 0.068%

    No Known Activations