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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 1079
    Prev
    Next
    INDEX
    Explanations

    terms related to events or actions showcasing celebration or enjoyment, particularly focused on activities involving parties, gatherings, or celebrations

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "key" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.88
    displayText
    -0.76
    PsyNetMessage
    -0.74
    IONS
    -0.70
    Ùħ
    -0.68
     Palestin
    -0.67
    70710
    -0.66
    ORED
    -0.66
    naire
    -0.66
    channelAvailability
    -0.65
    POSITIVE LOGITS
    eling
    0.99
    jriwal
    0.98
    erk
    0.95
    leen
    0.93
    ez
    0.92
    ller
    0.91
    ptic
    0.89
    llers
    0.89
    eter
    0.89
    rette
    0.89
    Activations Density 0.005%

    No Known Activations