© 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. 1734
    Prev
    Next
    INDEX
    Explanations

    proper nouns or phrases that are well-known or identified by specific terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "known" followed by specific terms or concepts

    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
    rentice
    -0.76
    otion
    -0.72
    plet
    -0.71
    ateurs
    -0.67
    olicy
    -0.67
    hibition
    -0.62
    erva
    -0.62
    ocaly
    -0.59
    poral
    -0.59
    prus
    -0.59
    POSITIVE LOGITS
    л
    0.85
     collectively
    0.79
     abbrevi
    0.75
    çīĪ
    0.75
    ":"","
    0.74
     Known
    0.73
    Els
    0.69
     aliases
    0.68
     abbre
    0.68
    later
    0.67
    Activations Density 0.034%

    No Known Activations