© 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. 13039
    Prev
    Next
    INDEX
    Explanations

    adjectives describing something delicate or easily damaged

    oai_token-act-pair · gpt-3.5-turbo

    references to fragility or vulnerability in various contexts

    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
    ilk
    -0.85
    upon
    -0.78
    ordan
    -0.78
    posted
    -0.76
    alach
    -0.75
    hig
    -0.73
    sen
    -0.72
    atography
    -0.71
    zig
    -0.71
    swick
    -0.70
    POSITIVE LOGITS
     adolesc
    1.12
     fragile
    1.05
     brittle
    0.89
     delicate
    0.77
     tiss
    0.76
     minded
    0.76
    adoes
    0.72
     masculinity
    0.72
    amental
    0.72
     vulner
    0.71
    Activations Density 0.013%

    No Known Activations