© 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. 11-RES-JB
    11. 9414
    Prev
    Next
    INDEX
    Explanations

    years or numbers associated with specific studies or events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to updates, releases, and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sbm
    -0.83
    âĹ¼
    -0.82
    POSE
    -0.76
    ÙIJ
    -0.72
    selves
    -0.69
     Athletic
    -0.67
    ãģĦ
    -0.67
    Mand
    -0.66
    agall
    -0.65
    NetMessage
    -0.65
    POSITIVE LOGITS
     expires
    1.02
     unavailable
    1.01
     includes
    0.99
     awaits
    0.98
     begins
    0.97
     survives
    0.93
     excludes
    0.92
     varies
    0.91
     replaces
    0.90
     applies
    0.89
    Activations Density 0.335%

    No Known Activations