© 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. 9-RES-JB
    11. 15644
    Prev
    Next
    INDEX
    Explanations

    It seems that neuron 4 is looking for names or terms related to specific places or persons

    oai_token-act-pair · gpt-3.5-turbo

    single character tokens or names with specific letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DERR
    -0.76
    APS
    -0.68
    BILITIES
    -0.62
    growth
    -0.61
    OTAL
    -0.59
    İĭ
    -0.58
    CLOSE
    -0.57
    lest
    -0.57
     somet
    -0.57
     rall
    -0.56
    POSITIVE LOGITS
    sted
    0.66
     Hospital
    0.65
     hybrids
    0.62
    heit
    0.62
    heid
    0.62
     combo
    0.61
     joint
    0.61
    ?????-
    0.60
    imore
    0.60
    enna
    0.59
    Activations Density 0.284%

    No Known Activations