© 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. 2-RES-JB
    11. 4413
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant events or developments following a specific circumstance or incident

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in the wake of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inates
    -0.75
    remlin
    -0.69
     Forbidden
    -0.65
     forbidden
    -0.64
    venants
    -0.62
     classified
    -0.61
    classified
    -0.60
    bis
    -0.59
     Lions
    -0.58
     reserved
    -0.57
    POSITIVE LOGITS
    fulness
    1.16
    wake
    1.14
    mares
    1.09
    achine
    0.97
     wake
    0.96
    bringer
    0.88
    idth
    0.82
    stead
    0.79
    own
    0.78
    pter
    0.78
    Activations Density 0.008%

    No Known Activations