© 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. 4814
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative emotional states

    oai_token-act-pair · gpt-3.5-turbo

    words related to aspects of espionage or conspiracy

    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
    forth
    -0.81
    matched
    -0.65
     Takeru
    -0.65
    elf
    -0.63
     Split
    -0.63
     ç¥ŀ
    -0.62
    riad
    -0.61
    animate
    -0.61
     Blessed
    -0.60
    houses
    -0.60
    POSITIVE LOGITS
    acies
    1.15
    atory
    1.10
    acles
    1.08
    acist
    1.03
    acular
    0.96
    acle
    0.95
    ysc
    0.95
    imental
    0.94
    acet
    0.94
    atorial
    0.93
    Activations Density 0.010%

    No Known Activations