© 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. 398
    Prev
    Next
    INDEX
    Explanations

    mentions of the proper noun "Jitan"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "Titan" and "Ivan" across various contexts

    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
    ategory
    -0.72
    bered
    -0.67
    thens
    -0.64
    pressure
    -0.64
    ¥ŀ
    -0.63
     Dise
    -0.62
    oney
    -0.62
    present
    -0.61
     deaf
    -0.61
    taboola
    -0.60
    POSITIVE LOGITS
    itan
    1.03
    osaurs
    1.00
    ica
    0.98
    ic
    0.88
    ienne
    0.87
    igans
    0.85
    ical
    0.82
    enburg
    0.82
    fall
    0.82
    ically
    0.80
    Activations Density 0.010%

    No Known Activations