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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 4383
    Prev
    Next
    INDEX
    Explanations

    references to a specific publication or news outlet named "Herald"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Herald" and variations of it related to news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perm
    -0.76
    entially
    -0.71
    ggie
    -0.69
    ential
    -0.69
    Ô
    -0.67
    ellen
    -0.67
    utm
    -0.65
    aeda
    -0.65
    riv
    -0.65
    olves
    -0.64
    POSITIVE LOGITS
     Tribune
    1.14
     Herald
    1.00
     Examiner
    0.83
    ry
    0.76
     Typ
    0.73
     Chronicle
    0.71
     Gazette
    0.70
    zeb
    0.69
     Globe
    0.68
     Newsp
    0.67
    Activations Density 0.011%

    No Known Activations