© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 10311
    Prev
    Next
    INDEX
    Explanations

    the word "ally" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ally" and its variations

    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
    umbers
    -0.87
    nutrition
    -0.76
    usage
    -0.76
    iday
    -0.75
    nit
    -0.75
    ammers
    -0.75
    arcity
    -0.74
    cale
    -0.74
    fitting
    -0.73
    omin
    -0.72
    POSITIVE LOGITS
     ally
    1.16
     Ally
    0.99
     allies
    0.88
    =]
    0.84
    ="#
    0.79
     darling
    0.78
     Allies
    0.78
    ãĥ¼ãĥĨ
    0.76
     comrade
    0.72
     overth
    0.72
    Activations Density 0.009%

    No Known Activations