© 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. 11-RES-JB
    11. 17633
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and procedures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the symbol 'âĢ', which likely indicate specific categories or classifications in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Manhattan
    -0.74
     Pilgrim
    -0.69
     Mous
    -0.68
     Schw
    -0.67
     Cycl
    -0.66
     Nam
    -0.64
     Moss
    -0.64
     Sony
    -0.63
     Mall
    -0.62
     Cameroon
    -0.61
    POSITIVE LOGITS
    ¬
    1.59
    ľ
    1.58
    ı
    1.37
    ¼
    1.33
    ĺ
    1.33
    ¯
    1.29
    Į
    1.28
    į
    1.25
    Ĵ
    1.25
    ®
    1.24
    Activations Density 0.201%

    No Known Activations