© 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. 7-RES-JB
    11. 13405
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the media outlet "FOX" in text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the FOX network

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abee
    -0.87
    ages
    -0.81
    iano
    -0.79
    idences
    -0.74
    arella
    -0.73
     Edison
    -0.73
    atton
    -0.71
    uates
    -0.69
    quished
    -0.69
    abus
    -0.69
    POSITIVE LOGITS
    CAST
    0.99
    DEN
    0.93
    ged
    0.86
    ĪĴ
    0.86
    çīĪ
    0.86
    ger
    0.83
    IUM
    0.82
    MAT
    0.82
    ging
    0.81
    strate
    0.81
    Activations Density 0.045%

    No Known Activations