© 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. 1-RES-JB
    11. 16896
    Prev
    Next
    INDEX
    Explanations

    phrases or words with special text characters, such as âĢ¸

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or mark (âĢ)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     detached
    -0.71
    ozy
    -0.63
    berman
    -0.63
    lder
    -0.62
     fragmentation
    -0.60
     scatter
    -0.59
     Truman
    -0.59
     redistribution
    -0.58
     mosqu
    -0.58
     transfer
    -0.58
    POSITIVE LOGITS
    âĸº
    0.98
    ¹
    0.98
    ij
    0.93
     âĢ
    0.92
    ł
    0.87
    IJ
    0.82
    ª
    0.81
    âĢ
    0.81
    âĢł
    0.80
    COMPLE
    0.80
    Activations Density 0.205%

    No Known Activations