© 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. 1-RES-JB
    11. 13962
    Prev
    Next
    INDEX
    Explanations

    variations and mentions of the name "Andreas"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Andreas" and variations of "asy" along with terms related to feelings of unease or conflict

    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
    fruit
    -0.75
    aciously
    -0.72
    capacity
    -0.70
     encour
    -0.69
    å§
    -0.69
    SIGN
    -0.68
    pool
    -0.68
    fare
    -0.67
    =#
    -0.66
    alcohol
    -0.65
    POSITIVE LOGITS
    merce
    0.94
    asy
    0.88
    pora
    0.87
    edia
    0.87
    insula
    0.83
    xual
    0.82
    iasco
    0.82
    uration
    0.79
    ederation
    0.79
    itars
    0.79
    Activations Density 0.029%

    No Known Activations