© 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. 3648
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to praise or admiration

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to expressions of encouragement or support

    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
    ascus
    -0.78
     disse
    -0.73
     convol
    -0.73
    plet
    -0.71
     awa
    -0.68
     pus
    -0.68
     barric
    -0.66
     drawer
    -0.66
     obstruct
    -0.65
    maxwell
    -0.63
    POSITIVE LOGITS
    LESS
    0.94
    FUL
    0.91
    ably
    0.89
    giving
    0.89
     Emin
    0.83
    fully
    0.82
    ful
    0.81
    frey
    0.80
     Glory
    0.80
     Excellence
    0.79
    Activations Density 0.189%

    No Known Activations