© 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. 13179
    Prev
    Next
    INDEX
    Explanations

    references to financial fees and costs

    oai_token-act-pair · gpt-3.5-turbo

    references to financial fees and charges

    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
    uve
    -0.71
     Sheen
    -0.71
    ocent
    -0.69
    noon
    -0.69
     Ange
    -0.69
    lihood
    -0.67
    ãĤ¨ãĥ«
    -0.64
     Flesh
    -0.64
     Paraly
    -0.64
    pse
    -0.63
    POSITIVE LOGITS
     fees
    1.24
     waivers
    1.02
     levied
    1.02
     incurred
    1.01
     payable
    1.00
    heet
    0.96
     fee
    0.91
     Fees
    0.86
     accrued
    0.83
    hooting
    0.83
    Activations Density 0.014%

    No Known Activations