© 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. 9235
    Prev
    Next
    INDEX
    Explanations

    words related to physical anguish

    oai_token-act-pair · gpt-3.5-turbo

    terms related to anguish and emotional distress

    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
    çīĪ
    -0.75
    bed
    -0.70
    noon
    -0.68
    gered
    -0.66
     PubMed
    -0.64
    TERN
    -0.64
    nesota
    -0.63
    nit
    -0.62
    £ı
    -0.62
    WARD
    -0.62
    POSITIVE LOGITS
    angu
    1.14
    anamo
    0.90
    inary
    0.89
    bernatorial
    0.88
    inces
    0.86
    ille
    0.86
    ingu
    0.85
    awei
    0.84
    ortium
    0.83
    emonium
    0.82
    Activations Density 0.009%

    No Known Activations