© 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. 7501
    Prev
    Next
    INDEX
    Explanations

    phrases related to saving time and effort

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to saving time and resources

    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
    apons
    -0.80
    ctuary
    -0.79
    soType
    -0.69
    ected
    -0.66
     Pigs
    -0.65
    stasy
    -0.64
    themed
    -0.63
     whistlebl
    -0.63
    claimed
    -0.61
    GROUP
    -0.61
    POSITIVE LOGITS
     hassle
    1.33
     costly
    1.25
     tedious
    1.22
     cumbersome
    1.16
     expensive
    1.12
     hoops
    1.10
     painstaking
    1.09
     ardu
    1.07
     unnecessarily
    1.05
     expense
    1.05
    Activations Density 0.756%

    No Known Activations