© 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. 9-RES-JB
    11. 15756
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases denoting amounts or quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe actions or consequences that "amount to" something significant

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arts
    -0.81
    utherland
    -0.76
    rers
    -0.75
    rot
    -0.74
    atu
    -0.74
     adjusts
    -0.72
    rose
    -0.72
    notations
    -0.71
    rients
    -0.70
    soon
    -0.70
    POSITIVE LOGITS
     heresy
    1.09
     blasphemy
    1.00
     treason
    0.98
     betrayal
    0.98
     manslaughter
    0.97
     genocide
    0.94
     extortion
    0.92
     bribery
    0.91
     blackmail
    0.89
     vandalism
    0.87
    Activations Density 0.148%

    No Known Activations