© 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. 11476
    Prev
    Next
    INDEX
    Explanations

    phrases related to far-off locations or events

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "horizon" and its variations

    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
    Cmd
    -0.63
    nia
    -0.63
     Sind
    -0.59
     Nickel
    -0.59
     voluntarily
    -0.59
     confess
    -0.58
     incorrectly
    -0.58
     Customs
    -0.57
    itis
    -0.57
     Random
    -0.54
    POSITIVE LOGITS
     horizon
    4.22
    izons
    1.75
     hor
    1.58
     Horizon
    1.50
     skyline
    1.42
     Horizons
    1.21
     roadmap
    1.19
     sunset
    1.12
     landscape
    1.09
     outlook
    1.04
    Activations Density 0.010%

    No Known Activations