© 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. 4-RES-JB
    11. 15262
    Prev
    Next
    INDEX
    Explanations

    references to video game consoles, particularly Nintendo consoles

    oai_token-act-pair · gpt-3.5-turbo

    references to Nintendo and its related gaming culture

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

    No Comments

    Negative Logits
    ablishment
    -0.74
    annis
    -0.73
    oning
    -0.69
    utherford
    -0.69
    oldemort
    -0.67
    aneers
    -0.63
    onies
    -0.63
    orget
    -0.61
     convict
    -0.61
     queens
    -0.61
    POSITIVE LOGITS
    Nintendo
    0.93
     Wii
    0.91
    intendo
    0.84
    Switch
    0.83
    ango
    0.80
    itsu
    0.79
    itive
    0.77
     Nintendo
    0.73
    nect
    0.72
    oji
    0.70
    Activations Density 0.005%

    No Known Activations