© 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. 3-RES-JB
    11. 10643
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or official titles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "owner" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eco
    -0.74
    ERA
    -0.69
    Bi
    -0.68
    urat
    -0.67
    held
    -0.65
    Ka
    -0.65
    auri
    -0.64
    hemat
    -0.63
    sheet
    -0.63
    Ward
    -0.62
    POSITIVE LOGITS
    oner
    1.25
    getic
    0.89
    \\\\
    0.88
     confir
    0.82
     extraord
    0.78
    geon
    0.77
    ODY
    0.74
    uther
    0.73
    ously
    0.72
    izabeth
    0.72
    Activations Density 0.012%

    No Known Activations