© 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. 24043
    Prev
    Next
    INDEX
    Explanations

    Japanese characters with occasional English words mixed in, possibly related to a specific text or language

    oai_token-act-pair · gpt-3.5-turbo

    specific non-Latin script characters or unusual symbols

    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
    chio
    -0.98
    achine
    -0.90
    ringe
    -0.90
    heastern
    -0.86
    lycer
    -0.82
    eways
    -0.81
    negie
    -0.80
    leground
    -0.79
    ateur
    -0.78
    nels
    -0.78
    POSITIVE LOGITS
    ãĤ
    1.19
    ãĤĵ
    1.18
    ãģĦ
    1.18
    ãĤĤ
    1.16
    ãģ
    1.15
    ãĢģ
    1.14
    ãģĤ
    1.13
    ãĢį
    1.09
    ãģ¯
    1.08
    æľ
    1.07
    Activations Density 0.006%

    No Known Activations