© 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. 0-RES-JB
    6. 14766
    Prev
    Next
    INDEX
    Explanations

    words related to things decreasing or deteriorating

    oai_token-act-pair · gpt-3.5-turbo

    the word "fell" and its various contexts

    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
    etta
    -0.74
     Wiley
    -0.71
    mot
    -0.68
    pecially
    -0.67
    CV
    -0.65
     [+
    -0.63
    Lock
    -0.62
     Lockheed
    -0.61
     Nano
    -0.60
    if
    -0.59
    POSITIVE LOGITS
     fell
    3.25
     falls
    2.03
     fallen
    1.85
     plummeted
    1.75
     fall
    1.73
     falling
    1.66
     collapsed
    1.63
     slipped
    1.47
     rose
    1.44
     plunged
    1.44
    Activations Density 0.012%

    No Known Activations