© 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. 10-RES-JB
    11. 7962
    Prev
    Next
    INDEX
    Explanations

    players and individuals mentioned as the best or suitable for specific roles or tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating opinions or beliefs about individuals' capabilities or performances in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.74
    laughter
    -0.72
     decree
    -0.69
     Restaur
    -0.67
     prohibitions
    -0.65
     COURT
    -0.64
     levied
    -0.63
     remem
    -0.63
     spills
    -0.61
     disclaimer
    -0.61
    POSITIVE LOGITS
     worthy
    1.34
     viable
    1.30
     suitable
    1.30
     deserving
    1.26
     capable
    1.19
     superior
    1.17
     worth
    1.17
    ready
    1.08
     adequate
    1.06
     worthwhile
    1.06
    Activations Density 0.547%

    No Known Activations