© 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. 6913
    Prev
    Next
    INDEX
    Explanations

    phrases related to renting, leasing, and renting out properties or items

    oai_token-act-pair · gpt-3.5-turbo

    terms related to renting and leasing properties or items

    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
    put
    -0.80
    vic
    -0.79
    bra
    -0.76
    atisf
    -0.73
    sis
    -0.73
    xual
    -0.72
    aminer
    -0.72
    eq
    -0.71
    mania
    -0.70
    clerosis
    -0.70
    POSITIVE LOGITS
     copies
    0.89
     copyrighted
    0.85
     extensively
    0.77
     artwork
    0.76
     DVDs
    0.75
     farmland
    0.74
     goods
    0.73
     condoms
    0.73
     gifts
    0.72
     tickets
    0.72
    Activations Density 0.143%

    No Known Activations