© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 23321
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific word or phrase "Sl9"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence "Sl" followed by a number, likely indicating references to specific movies or shows related to a recurring theme or franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICLE
    -0.93
    ãģ®éŃĶ
    -0.93
    æĦ
    -0.81
    åĤ
    -0.79
    å§«
    -0.77
    enegger
    -0.74
     Samar
    -0.73
    BLIC
    -0.73
    OLOGY
    -0.70
    èĪ
    -0.69
    POSITIVE LOGITS
    ippery
    1.04
    ashes
    1.03
    ither
    0.99
    ips
    0.97
    irts
    0.96
    oppy
    0.96
    inking
    0.96
    ipper
    0.94
    ickers
    0.92
    ink
    0.92
    Activations Density 0.004%

    No Known Activations