© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 7566
    Prev
    Next
    INDEX
    Explanations

    words related to being impacted or affected by various events or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being affected or impacted by events or circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cia
    -0.64
    alt
    -0.63
    çĦ
    -0.62
    pires
    -0.61
    cipled
    -0.59
    apult
    -0.59
     Fargo
    -0.58
     aspiration
    -0.58
    fetched
    -0.58
    Alias
    -0.57
    POSITIVE LOGITS
     adversely
    1.22
     by
    1.14
     negatively
    1.12
     materially
    0.92
     disproportionately
    0.91
     financially
    0.88
     severely
    0.86
     acutely
    0.85
    by
    0.85
     greatly
    0.85
    Activations Density 0.069%

    No Known Activations