© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    6. 17915
    Prev
    Next
    INDEX
    Explanations

    words related to formal statements or positions

    oai_token-act-pair · gpt-3.5-turbo

    references to authority or official status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MpServer
    -0.70
    hes
    -0.70
    leep
    -0.70
    $$
    -0.68
    raised
    -0.65
     prey
    -0.65
    raise
    -0.65
    Rand
    -0.65
    berries
    -0.63
    qv
    -0.63
    POSITIVE LOGITS
     official
    3.64
    official
    2.76
     Official
    2.67
    Official
    2.29
     unofficial
    2.13
     OFFIC
    1.84
     officially
    1.77
    offic
    1.58
     officials
    1.51
     Officials
    1.43
    Activations Density 0.027%

    No Known Activations