© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1236
    Prev
    Next
    INDEX
    Explanations

    words related to describing and discussing various situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to the state or condition of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Creed
    -0.78
     Included
    -0.72
    enary
    -0.71
     purchases
    -0.69
    issions
    -0.69
     Instruction
    -0.68
    packs
    -0.67
     caches
    -0.66
    ission
    -0.65
     acknowled
    -0.63
    POSITIVE LOGITS
     dire
    1.40
     precarious
    1.39
     worsening
    1.35
     deteriorating
    1.34
     intolerable
    1.30
     bleak
    1.23
     worsened
    1.23
     tense
    1.22
     perilous
    1.17
     unfavorable
    1.15
    Activations Density 0.169%

    No Known Activations