© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 12414
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases indicating desires or intentions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of intention and desire related to goals and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    river
    -0.84
     Marino
    -0.67
     Lima
    -0.64
     Pak
    -0.64
     Mellon
    -0.62
    banks
    -0.60
     Fey
    -0.59
     Bett
    -0.59
     floods
    -0.58
    riot
    -0.58
    POSITIVE LOGITS
     accomplish
    1.13
     achieve
    1.06
     emulate
    0.98
     improve
    0.95
     conserve
    0.89
     eliminate
    0.87
     learn
    0.84
     solve
    0.84
     introduce
    0.83
     bring
    0.83
    Activations Density 0.160%

    No Known Activations