© 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. 6079
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names related to the name "George/Georg" and "Philip/Philipp"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific names, particularly "Georg" and "Philipp."

    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
    pled
    -0.74
    footed
    -0.71
     lodge
    -0.67
    etition
    -0.65
    byte
    -0.64
    ACK
    -0.59
    fork
    -0.59
     complicity
    -0.59
     marrow
    -0.58
    NES
    -0.58
    POSITIVE LOGITS
    ians
    1.01
    opol
    0.98
    Ī
    0.89
    iev
    0.84
    ī
    0.84
    inos
    0.83
    Īè
    0.82
    ina
    0.81
    iana
    0.81
    opoulos
    0.80
    Activations Density 0.054%

    No Known Activations