© 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. 9-RES-JB
    11. 9108
    Prev
    Next
    INDEX
    Explanations

    words related to hazardous or dangerous situations

    oai_token-act-pair · gpt-3.5-turbo

    adjectives ending in 'ous'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NPR
    -0.68
    nery
    -0.66
    ellen
    -0.64
    inav
    -0.64
    iche
    -0.59
    asonic
    -0.59
    zig
    -0.58
    anz
    -0.58
    agall
    -0.58
    OY
    -0.58
    POSITIVE LOGITS
    Magikarp
    1.40
    ness
    1.13
    nesses
    0.93
    NESS
    0.84
    ity
    0.80
    lihood
    0.80
    rontal
    0.78
     oxide
    0.73
    sis
    0.73
    ous
    0.72
    Activations Density 0.072%

    No Known Activations