© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 7839
    Prev
    Next
    INDEX
    Explanations

    verbs related to the action of renewing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "renew" and its variations

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

    No Comments

    Negative Logits
    ahi
    -0.80
    uchs
    -0.75
    ohm
    -0.74
    pper
    -0.74
    onne
    -0.69
     Printed
    -0.68
    ramid
    -0.68
    otropic
    -0.67
    dor
    -0.66
     Hedge
    -0.65
    POSITIVE LOGITS
     renew
    1.28
     renewal
    1.20
     renewed
    1.01
     lease
    0.87
     vig
    0.86
     tremend
    0.85
     vitality
    0.83
     confir
    0.82
    ably
    0.82
     warr
    0.81
    Activations Density 0.013%

    No Known Activations