© 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. 8-RES-JB
    11. 6918
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or situations happening without something essential

    oai_token-act-pair · gpt-3.5-turbo

    phrases that culminate in the expression "without a."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estate
    -0.84
    geist
    -0.78
     âĢº
    -0.75
    ãĥĩ
    -0.75
    adr
    -0.75
    ahime
    -0.71
    ãĥ³ãĤ¸
    -0.71
    ogyn
    -0.68
    worth
    -0.67
     Rates
    -0.67
    POSITIVE LOGITS
     doubt
    0.96
     interruption
    0.95
     supervision
    0.88
     exception
    0.87
     pesky
    0.86
     intervention
    0.85
     permission
    0.84
     accompanying
    0.83
     hesitation
    0.82
     mention
    0.82
    Activations Density 0.105%

    No Known Activations