Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 4475
    Prev
    Next
    INDEX
    Explanations

    words related to the horizon or future events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "horizon."

    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
    hiro
    -0.79
    ERC
    -0.78
    aud
    -0.78
    UGC
    -0.78
    ublic
    -0.75
    piracy
    -0.75
    ymph
    -0.72
    verbs
    -0.72
    GB
    -0.71
    ough
    -0.70
    POSITIVE LOGITS
     horizon
    1.59
    izons
    1.22
     sunset
    0.78
     horizont
    0.78
     wip
    0.77
    izon
    0.77
     skyline
    0.76
     cannabin
    0.76
     unlaw
    0.75
     lobe
    0.71
    Activations Density 0.004%

    No Known Activations