© 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. 4398
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of permanence or continuity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to permanence and consistency

    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
     darn
    -0.67
    PIN
    -0.66
    ACA
    -0.64
    soDeliveryDate
    -0.64
     unbeat
    -0.62
     caps
    -0.61
     bundled
    -0.61
    papers
    -0.61
     pronounced
    -0.60
     capped
    -0.59
    POSITIVE LOGITS
    tarian
    0.96
    terday
    0.94
    nesses
    0.94
     Affairs
    0.83
    ansion
    0.82
     Investigation
    0.81
    iasm
    0.77
    uality
    0.76
    phrine
    0.76
    tenance
    0.74
    Activations Density 0.058%

    No Known Activations