© 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. 2027
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "slumber."

    oai_token-act-pair · gpt-3.5-turbo

    words related to "sl" as a prefix, likely focusing on variations of the word "slum" or "sluggish."

    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
    ICLE
    -0.84
    enegger
    -0.74
    IFIC
    -0.73
    ãģ®éŃĶ
    -0.70
     Cause
    -0.68
     Kirin
    -0.67
    姫
    -0.66
    BLIC
    -0.65
    éļ
    -0.65
    HCR
    -0.65
    POSITIVE LOGITS
    udge
    1.16
    anted
    1.14
    ugg
    1.14
    ashes
    1.12
    otted
    1.12
    ither
    1.12
    inging
    1.11
    ipp
    1.11
    ipper
    1.11
    asher
    1.10
    Activations Density 0.008%

    No Known Activations