© 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. 2-RES-JB
    11. 3925
    Prev
    Next
    INDEX
    Explanations

    references to competitors or enemies in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to competition or opposing entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udeb
    -0.78
    ADD
    -0.70
    olia
    -0.69
    uggage
    -0.67
    RGB
    -0.67
    ALT
    -0.67
    acca
    -0.66
    ortunate
    -0.65
    umatic
    -0.65
    Hat
    -0.64
    POSITIVE LOGITS
     rival
    1.19
     rivals
    1.14
    ries
    1.04
     challengers
    0.93
     competitor
    0.92
     competitors
    0.90
     adversaries
    0.80
     challenger
    0.78
     rivalry
    0.78
    untled
    0.78
    Activations Density 0.014%

    No Known Activations