© 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. 0-RES-JB
    11. 20287
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences with instructions or steps

    oai_token-act-pair · gpt-3.5-turbo

    a specific Unicode character often used as a bullet point or section separator

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ``
    -1.20
     �
    -1.11
     ''
    -0.94
    �
    -0.80
     _
    -0.75
    ĪĴ
    -0.72
     ``(
    -0.67
    ²¾
    -0.65
     `
    -0.63
    ``
    -0.63
    POSITIVE LOGITS
    âĢ¦
    3.43
    âĢ¦.
    2.88
    âĢ¦"
    2.84
    âĢ¦)
    2.68
    âĢ¦..
    2.65
     âĢ¦
    2.59
    "âĢ¦
    2.54
    âĢ¦]
    2.53
    âĢ¦."
    2.42
     [âĢ¦]
    2.40
    Activations Density 0.024%

    No Known Activations