© 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. 8-RES-JB
    11. 3128
    Prev
    Next
    INDEX
    Explanations

    keywords related to renewal or restarting

    oai_token-act-pair · gpt-3.5-turbo

    words related to renewal and membership updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahi
    -0.77
    ecause
    -0.76
    adr
    -0.75
    onne
    -0.73
    pper
    -0.71
    erity
    -0.69
    uchs
    -0.68
    otropic
    -0.66
    istics
    -0.66
    mop
    -0.64
    POSITIVE LOGITS
     renew
    0.89
    foundland
    0.86
     renewal
    0.82
     lease
    0.80
    escent
    0.79
    CLASSIFIED
    0.78
     vig
    0.77
    ly
    0.75
    uberty
    0.74
     renewed
    0.74
    Activations Density 0.051%

    No Known Activations