© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4137
    Prev
    Next
    INDEX
    Explanations

    names or references related to "Bass."

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the surname "Bass" as well as their associates

    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
     cipher
    -0.74
     hol
    -0.72
    worms
    -0.71
     resil
    -0.70
     rune
    -0.69
     sten
    -0.69
     foreskin
    -0.69
     undead
    -0.68
     translucent
    -0.68
     scram
    -0.67
    POSITIVE LOGITS
     Bass
    3.28
     Bark
    1.41
     Barker
    1.27
     Singer
    1.27
     Archer
    1.22
     Mash
    1.13
     Chapman
    1.13
     Kass
    1.12
     Cantor
    1.10
     Paddock
    1.03
    Activations Density 0.034%

    No Known Activations