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. 7-RES-JB
    6. 7114
    Prev
    Next
    INDEX
    Explanations

    words related to music genres and cultural connections

    oai_token-act-pair · gpt-3.5-turbo

    references to hip-hop culture and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nces
    -0.78
    é¾
    -0.76
    ulhu
    -0.71
    ãĥ¬
    -0.70
    ãĥ´ãĤ¡
    -0.69
    inelli
    -0.69
     destro
    -0.68
    ctica
    -0.68
     Purg
    -0.67
    Cmd
    -0.66
    POSITIVE LOGITS
    ween
    0.85
    bay
    0.70
    awei
    0.67
    Adult
    0.66
    bour
    0.66
    hunt
    0.66
    hop
    0.64
    Hop
    0.64
    ish
    0.64
    horn
    0.63
    Activations Density 0.202%

    No Known Activations