© 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. 4032
    Prev
    Next
    INDEX
    Explanations

    references to decision-making processes

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of decision-making

    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
     bun
    -0.62
     Cortex
    -0.60
     Mono
    -0.60
     seeded
    -0.60
    ulet
    -0.59
    ARS
    -0.56
     plentiful
    -0.56
     Lar
    -0.55
     KS
    -0.55
     slee
    -0.55
    POSITIVE LOGITS
    theless
    1.14
    tenance
    0.95
    tons
    0.84
    aukee
    0.84
    etting
    0.82
    intensive
    0.81
    rontal
    0.79
    folios
    0.79
    antry
    0.78
    dating
    0.77
    Activations Density 0.072%

    No Known Activations