© 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. 11-RES-JB
    11. 9942
    Prev
    Next
    INDEX
    Explanations

    words related to truth or honesty

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of truth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elig
    -0.68
     Pharm
    -0.64
     Spice
    -0.61
     fin
    -0.61
     Turk
    -0.57
     disadvant
    -0.57
     Sto
    -0.57
     Peninsula
    -0.57
     Krish
    -0.57
    uled
    -0.56
    POSITIVE LOGITS
    fulness
    1.61
    fully
    1.28
    iness
    1.10
    telling
    1.06
     serum
    1.00
    about
    0.97
    ful
    0.96
    ulence
    0.94
    seekers
    0.90
    orial
    0.88
    Activations Density 0.041%

    No Known Activations