© 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. 7269
    Prev
    Next
    INDEX
    Explanations

    expressions related to enjoyment or pleasure

    oai_token-act-pair · gpt-3.5-turbo

    expressions of enjoyment and positive experiences

    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
    requires
    -0.88
    apons
    -0.81
    æ©Ł
    -0.74
    Downloadha
    -0.73
    İĭ
    -0.72
    pmwiki
    -0.71
    licts
    -0.70
    Myth
    -0.69
    rupulous
    -0.68
    èĥ
    -0.66
    POSITIVE LOGITS
     sailing
    0.93
     seeing
    0.87
     filming
    0.87
     watching
    0.86
     discovering
    0.81
     rehears
    0.81
     timing
    0.79
     chatting
    0.79
     initially
    0.79
     organising
    0.79
    Activations Density 0.266%

    No Known Activations