© 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. 22601
    Prev
    Next
    INDEX
    Explanations

    references to The Washington Post newspaper

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "The Washington Post."

    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
    imilar
    -0.68
     asses
    -0.67
    è£
    -0.66
    akuya
    -0.64
     evapor
    -0.64
     infiltr
    -0.63
     cultiv
    -0.61
    hun
    -0.61
    ilty
    -0.60
    cffffcc
    -0.60
    POSITIVE LOGITS
     Post
    3.79
    Post
    2.80
    post
    2.45
     post
    2.10
     POST
    1.93
     Posts
    1.53
    POST
    1.50
     Postal
    1.44
     posts
    1.39
     Times
    1.37
    Activations Density 0.019%

    No Known Activations