© 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. 2719
    Prev
    Next
    INDEX
    Explanations

    references to superlatives or rankings of entities

    oai_token-act-pair · gpt-3.5-turbo

    plural nouns that refer to significant entities or groups

    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
     Lauder
    -0.71
    ertodd
    -0.63
    xual
    -0.62
    CLAIM
    -0.59
    epad
    -0.58
     ..............
    -0.58
     Packs
    -0.57
     resigned
    -0.57
    EVA
    -0.57
     Ital
    -0.57
    POSITIVE LOGITS
     tallest
    1.03
     largest
    1.02
     longest
    0.92
    largest
    0.89
     foremost
    0.88
     biggest
    0.86
     premiere
    0.86
    selves
    0.86
     poorest
    0.86
     Greatest
    0.85
    Activations Density 0.112%

    No Known Activations