© 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. 0-RES-JB
    11. 23150
    Prev
    Next
    INDEX
    Explanations

    phrases related to intentional or deliberate actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intent, specifically focusing on deliberate and intentional actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubi
    -0.70
    hel
    -0.67
     outper
    -0.66
    ihu
    -0.65
    enium
    -0.65
    peg
    -0.64
     excel
    -0.64
    beans
    -0.63
    orf
    -0.61
    orb
    -0.60
    POSITIVE LOGITS
     deliberate
    3.30
     intentional
    2.79
     unintentional
    1.96
     willful
    1.80
     conscious
    1.57
     accidental
    1.54
     systematic
    1.51
     concerted
    1.43
     inadvert
    1.37
     negligent
    1.33
    Activations Density 0.029%

    No Known Activations