© 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. 24193
    Prev
    Next
    INDEX
    Explanations

    references to textual content, such as text messages or written text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "text."

    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
    pload
    -0.71
    vre
    -0.70
     CVE
    -0.67
    dL
    -0.67
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.66
     clamp
    -0.64
     Drone
    -0.62
     notor
    -0.61
    avement
    -0.61
     Parenthood
    -0.60
    POSITIVE LOGITS
     text
    1.15
     texts
    1.13
    text
    1.05
    ured
    1.04
    books
    0.96
     Text
    0.94
    book
    0.93
    area
    0.90
     messages
    0.88
    urized
    0.88
    Activations Density 0.012%

    No Known Activations