© 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. 9-RES-JB
    6. 5699
    Prev
    Next
    INDEX
    Explanations

    the verb "to be" followed by a descriptive word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    recurrent phrases related to time and measurement

    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
     UID
    -0.65
     NEVER
    -0.62
    UID
    -0.60
     Annotations
    -0.59
    stuff
    -0.58
     FANT
    -0.56
    ****************
    -0.56
     Firstly
    -0.55
    ?:
    -0.55
     ONE
    -0.55
    POSITIVE LOGITS
     theirs
    0.86
     hers
    0.82
     likewise
    0.77
    aeus
    0.63
    inery
    0.58
     summers
    0.57
    redit
    0.56
     emulate
    0.55
    ffee
    0.54
     oven
    0.54
    Activations Density 0.634%

    No Known Activations