© 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. 2662
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the character "Ļ" and related variations, likely indicating emphasis or special significance

    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
    rolet
    -0.65
     contempor
    -0.59
     disenfranch
    -0.58
     pir
    -0.58
     decomp
    -0.57
     shack
    -0.57
     legality
    -0.57
     subord
    -0.56
     hob
    -0.55
     warr
    -0.54
    POSITIVE LOGITS
    t
    0.98
    s
    0.97
    º
    0.93
    ¹
    0.89
    âĶĢ
    0.85
    ivably
    0.83
    u
    0.83
    ¨
    0.82
    ationally
    0.82
    ulty
    0.79
    Activations Density 0.138%

    No Known Activations