© 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. 1-RES-JB
    11. 13484
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names or identities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "James."

    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
    ŃĶ
    -0.75
     intraven
    -0.69
     mobility
    -0.66
     probable
    -0.66
     quart
    -0.65
     selective
    -0.64
     refrigerator
    -0.64
     knife
    -0.64
     conviction
    -0.63
     compr
    -0.63
    POSITIVE LOGITS
    ames
    1.93
    ame
    1.26
    aming
    1.02
    amed
    1.00
    erver
    0.96
    paces
    0.94
    eting
    0.90
    AMES
    0.87
    eters
    0.86
    ername
    0.85
    Activations Density 0.002%

    No Known Activations