© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 10134
    Prev
    Next
    INDEX
    Explanations

    mention of the word "Frozen"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Frozen" franchise and its characters or related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oses
    -0.79
    ahon
    -0.76
    escription
    -0.75
    abal
    -0.75
    lers
    -0.74
    alach
    -0.71
    ours
    -0.71
    onal
    -0.68
    een
    -0.67
    ãĥ£
    -0.67
    POSITIVE LOGITS
    Elsa
    0.82
     Sparkle
    0.72
     cust
    0.70
    cess
    0.69
    lander
    0.68
     yogurt
    0.67
     Elsa
    0.67
     bean
    0.67
     Princess
    0.66
     Claus
    0.66
    Activations Density 0.066%

    No Known Activations