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

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 16966
    Prev
    Next
    INDEX
    Explanations

    words related to musicians or bands

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Jagger" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kind
    -0.74
    matter
    -0.74
     Surv
    -0.71
     Cf
    -0.69
    ĻĤ
    -0.68
     Vide
    -0.67
    »Ĵ
    -0.67
     Watching
    -0.65
     Constantin
    -0.65
    erva
    -0.64
    POSITIVE LOGITS
    agger
    1.10
    reys
    0.80
    mentation
    0.79
    cade
    0.77
    ashtra
    0.76
    butt
    0.76
    istas
    0.72
    DX
    0.71
    dinand
    0.70
    riott
    0.68
    Activations Density 0.014%

    No Known Activations