© 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. 11-RES-JB
    11. 22475
    Prev
    Next
    INDEX
    Explanations

    references or mentions of 'The Guardian' newspaper

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the publication "The Guardian"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.76
    itionally
    -0.69
     Mn
    -0.67
    atically
    -0.66
     neighboring
    -0.66
    perm
    -0.64
     joints
    -0.64
     waivers
    -0.64
    tions
    -0.64
    inant
    -0.63
    POSITIVE LOGITS
     newspaper
    1.23
     Newspaper
    1.08
     Newsp
    1.04
     Editorial
    1.00
     Angels
    0.96
     Online
    0.92
     columnist
    0.91
     tabloid
    0.91
     editorial
    0.89
     Telegraph
    0.87
    Activations Density 0.072%

    No Known Activations