© 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. 0-RES-JB
    11. 13196
    Prev
    Next
    INDEX
    Explanations

    phrases or entities related to names or proper nouns, particularly ones starting with "Al"

    oai_token-act-pair · gpt-3.5-turbo

    the mention of the name "Al" or references to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     penis
    -0.69
     grabs
    -0.67
     pav
    -0.67
     Ghostbusters
    -0.65
     brist
    -0.65
     scripted
    -0.65
     pim
    -0.64
     genitals
    -0.63
     dick
    -0.63
     bust
    -0.63
    POSITIVE LOGITS
    Al
    3.55
     Al
    2.10
    Ale
    1.53
    AL
    1.53
    Ali
    1.41
     AL
    1.36
    Ab
    1.36
     Alb
    1.35
     al
    1.33
    Ari
    1.30
    Activations Density 0.011%

    No Known Activations