© 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. 8887
    Prev
    Next
    INDEX
    Explanations

    phrases related to industries or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to "industry" or related terms

    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
    cca
    -0.77
    asure
    -0.73
    grade
    -0.71
    ilts
    -0.71
     rapp
    -0.69
    asus
    -0.67
     quarters
    -0.66
    grading
    -0.66
    zie
    -0.66
    asures
    -0.64
    POSITIVE LOGITS
    IND
    1.18
    STATE
    1.04
    MAP
    0.97
    ERG
    0.93
    ERS
    0.93
    ERE
    0.89
    NESS
    0.88
     IND
    0.87
    ERAL
    0.86
    ESS
    0.86
    Activations Density 0.007%

    No Known Activations