© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6367
    Prev
    Next
    INDEX
    Explanations

    phrases relating to strength, importance, or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Dignitas" and related terms, often in the context of organizational references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itary
    -1.18
     Yuan
    -0.71
    pport
    -0.70
    Publisher
    -0.70
    sbm
    -0.69
    Rated
    -0.68
     kindred
    -0.68
    ategory
    -0.65
    ãĢIJ
    -0.65
     tariff
    -0.64
    POSITIVE LOGITS
    itas
    3.22
    alis
    1.56
    idis
    1.33
    ilon
    1.24
    ulus
    1.21
    anos
    1.15
    amus
    1.15
    amia
    1.11
    uca
    1.08
    isma
    1.05
    Activations Density 0.033%

    No Known Activations