© 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. 6-RES-JB
    11. 24416
    Prev
    Next
    INDEX
    Explanations

    verbs ending in 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    specific forms of the word "bask" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alias
    -0.77
     mortg
    -0.69
    clud
    -0.69
    pool
    -0.65
    spec
    -0.65
    ilty
    -0.64
    rella
    -0.62
    pictured
    -0.62
    uild
    -0.62
    loader
    -0.61
    POSITIVE LOGITS
     brunt
    0.95
     Flavoring
    0.92
     gunfire
    0.87
     breeze
    0.84
     vibrations
    0.82
     electromagnetic
    0.81
     incoming
    0.79
     hearing
    0.79
     stimuli
    0.78
    waves
    0.78
    Activations Density 0.478%

    No Known Activations