© 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. 2-RES-JB
    11. 13017
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations and events such as TED talks and ALEC (American Legislative Exchange Council)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of TED events and initiatives, as well as references to STEM and ALEC

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acht
    -0.72
    metics
    -0.72
    rosc
    -0.71
    alities
    -0.70
    afort
    -0.69
    Ö¼
    -0.65
    roman
    -0.65
    antine
    -0.64
    regn
    -0.64
    heny
    -0.64
    POSITIVE LOGITS
    TED
    1.04
     TED
    0.93
    MED
    0.91
    ESCO
    0.90
    ãĤ¼ãĤ¦ãĤ¹
    0.90
     Talks
    0.86
    CAN
    0.85
    SW
    0.84
    CRIPTION
    0.84
    IAS
    0.83
    Activations Density 0.017%

    No Known Activations