© 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. 7-RES-JB
    11. 8645
    Prev
    Next
    INDEX
    Explanations

    sequences with special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols interspersed in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     detached
    -0.69
    conservancy
    -0.68
     shack
    -0.66
     sacrific
    -0.66
     fed
    -0.65
     interf
    -0.64
     gad
    -0.64
     shroud
    -0.63
     respir
    -0.63
     scene
    -0.62
    POSITIVE LOGITS
    ¹
    0.99
    į
    0.96
    Ī
    0.93
    ¬
    0.89
    ı
    0.89
    º
    0.88
    §
    0.88
    say
    0.88
    ¡
    0.86
    ĭ
    0.84
    Activations Density 0.216%

    No Known Activations