© 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. 10-RES-JB
    11. 20357
    Prev
    Next
    INDEX
    Explanations

    phrases related to goals, objectives, intentions, and promises

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to intentions, policies, promises, and objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asus
    -0.63
    osi
    -0.56
    culosis
    -0.55
    AGES
    -0.55
     Shooter
    -0.54
    nant
    -0.54
    odor
    -0.54
    ARS
    -0.54
    cer
    -0.54
    bilt
    -0.54
    POSITIVE LOGITS
    heet
    1.14
    cale
    1.12
    mith
    1.05
    pring
    1.05
    etting
    1.04
    etter
    0.99
    paces
    0.99
     regarding
    0.98
    uggest
    0.96
    cape
    0.96
    Activations Density 0.303%

    No Known Activations