Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21555
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to extreme or dangerous situations

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing conditions or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ellen
    -0.79
    ARC
    -0.76
    NPR
    -0.73
     Psychiat
    -0.68
    ueller
    -0.68
    NER
    -0.67
    NF
    -0.67
    OWS
    -0.67
    âĸ¬âĸ¬
    -0.67
    GM
    -0.66
    POSITIVE LOGITS
    Magikarp
    1.32
    ous
    1.08
    ness
    1.07
     amounts
    0.89
    ity
    0.86
    lihood
    0.86
    ly
    0.84
     endeavour
    0.80
    lly
    0.79
     endeavors
    0.78
    Activations Density 0.019%

    No Known Activations