© 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. 4-RES-JB
    11. 14792
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that end with specific Unicode characters like "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    structured legal language and references to legal concepts or terms

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

    No Comments

    Negative Logits
     regenerate
    -0.79
     teleport
    -0.75
     plunge
    -0.73
     regener
    -0.70
     hooked
    -0.68
     finishing
    -0.68
     stomp
    -0.68
     diving
    -0.67
     adventures
    -0.67
     travelling
    -0.67
    POSITIVE LOGITS
    Specifically
    1.13
    Article
    1.12
    However
    1.10
    Moreover
    1.05
    According
    1.05
    ccording
    1.05
    Newsletter
    1.04
    Furthermore
    1.04
    Section
    1.03
    Thus
    1.02
    Activations Density 0.874%

    No Known Activations