© 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. 17720
    Prev
    Next
    INDEX
    Explanations

    words related to a specific person or entity, specifically someone or something named "Isi"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "ISI" (Inter-Services Intelligence) or related references

    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
    table
    -0.74
    nd
    -0.73
    dream
    -0.70
    fair
    -0.66
    worthy
    -0.65
    chain
    -0.65
    proof
    -0.65
    MW
    -0.65
    graph
    -0.64
    story
    -0.64
    POSITIVE LOGITS
    isi
    1.36
    ón
    0.88
    orno
    0.80
    agate
    0.80
    orescence
    0.80
     guiActiveUn
    0.80
    qi
    0.79
    ë
    0.78
    obar
    0.76
    án
    0.74
    Activations Density 0.006%

    No Known Activations