© 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. 2-RES-JB
    11. 19439
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to specific locations or entities such as "Nos" and "Wyn."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Nos" or variations of it, which may indicate a focus on a specific entity or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vantage
    -0.80
    riel
    -0.75
    assies
    -0.75
    onomous
    -0.70
    owered
    -0.68
     Archdemon
    -0.67
    regn
    -0.65
    qua
    -0.64
    ------------
    -0.63
    board
    -0.63
    POSITIVE LOGITS
    uits
    0.85
    teenth
    0.83
    cha
    0.81
    creen
    0.80
    adequ
    0.76
    uit
    0.75
    umbers
    0.74
    cale
    0.74
    ieth
    0.71
    ppo
    0.71
    Activations Density 0.024%

    No Known Activations