© 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. 0-RES-JB
    11. 20409
    Prev
    Next
    INDEX
    Explanations

    phrases containing the name "Imi" or "Latiimer" predominantly

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Imi" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colleges
    -0.68
    CAST
    -0.63
     services
    -0.61
     Sixers
    -0.60
     Cricket
    -0.59
     kinderg
    -0.59
     stakes
    -0.59
     Colleges
    -0.59
     Cast
    -0.59
     Athe
    -0.59
    POSITIVE LOGITS
    imi
    4.19
    imo
    2.13
    im
    2.01
    imer
    2.00
    imus
    1.95
    ima
    1.83
    imir
    1.83
    imov
    1.68
    imen
    1.59
    imize
    1.53
    Activations Density 0.006%

    No Known Activations