© 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. 7-RES-JB
    11. 21156
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "senior"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sen" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anked
    -0.74
    atform
    -0.68
     hitch
    -0.61
    ATHER
    -0.60
     Pwr
    -0.60
     multinational
    -0.59
     Cind
    -0.59
    OSS
    -0.58
    legged
    -0.58
     grounding
    -0.58
    POSITIVE LOGITS
    pai
    1.51
    iors
    1.19
    egal
    1.11
    seless
    1.06
    ocide
    1.03
    escent
    1.02
    esis
    0.91
    kov
    0.90
    hov
    0.88
    ryu
    0.86
    Activations Density 0.035%

    No Known Activations