© 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. 9-RES-JB
    11. 16424
    Prev
    Next
    INDEX
    Explanations

    informal or casual adjectives used to describe things positively

    oai_token-act-pair · gpt-3.5-turbo

    words associated with playful or whimsical characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieved
    -0.78
    ainer
    -0.75
    auer
    -0.73
    hower
    -0.72
    IVER
    -0.72
    avering
    -0.72
    ieves
    -0.72
    ugal
    -0.71
    accompan
    -0.70
    hips
    -0.70
    POSITIVE LOGITS
     little
    1.05
     stuff
    1.03
    pmwiki
    0.98
     gimm
    0.97
     bastard
    0.97
     shit
    0.94
     acron
    0.93
     jokes
    0.93
     nick
    0.91
     crap
    0.91
    Activations Density 0.200%

    No Known Activations