© 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. 2712
    Prev
    Next
    INDEX
    Explanations

    mentions of personal possessions or viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    references to personal ownership or possession

    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
     apiece
    -0.84
    itect
    -0.81
    illac
    -0.72
    ibaba
    -0.72
     Uriel
    -0.68
     guiIcon
    -0.68
     respectively
    -0.65
    arians
    -0.64
    aphael
    -0.64
    ãħĭ
    -0.63
    POSITIVE LOGITS
    anmar
    1.26
     own
    1.23
    stery
    1.21
    ocard
    1.16
    opic
    1.16
    opia
    1.13
     favorite
    1.10
     wife
    1.08
     dad
    1.06
     colleague
    1.05
    Activations Density 0.144%

    No Known Activations