© 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. 8072
    Prev
    Next
    INDEX
    Explanations

    phrases related to prisons

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "Prison."

    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
    GY
    -0.83
     Scotia
    -0.82
     logger
    -0.68
    icago
    -0.66
     nerves
    -0.63
     deed
    -0.62
     tune
    -0.62
    astical
    -0.61
    Bra
    -0.61
    peed
    -0.60
    POSITIVE LOGITS
    ers
    1.15
     Prison
    1.11
    er
    0.92
    ership
    0.91
     Architect
    0.84
    prison
    0.84
    eral
    0.80
    sylvania
    0.80
    neys
    0.80
    Exec
    0.80
    Activations Density 0.009%

    No Known Activations