© 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. 3-RES-JB
    6. 12038
    Prev
    Next
    INDEX
    Explanations

    phrases related to suffocation or intense pressure

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of suffering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    senal
    -0.76
     Dragonbound
    -0.75
    REDACTED
    -0.71
    TAG
    -0.67
    CHR
    -0.66
    Ô
    -0.65
     Ally
    -0.63
    CLASSIFIED
    -0.63
     Logan
    -0.63
    displayText
    -0.63
    POSITIVE LOGITS
    erers
    1.18
    erer
    1.01
    ocating
    1.00
    ishers
    0.97
    iments
    0.95
     suff
    0.93
    ocation
    0.90
    ishing
    0.89
    ishes
    0.88
    ocated
    0.86
    Activations Density 0.010%

    No Known Activations