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. 1-RES-JB
    6. 23785
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "dagger" and names related to Mick Jagger

    oai_token-act-pair · gpt-3.5-turbo

    references to characters associated with the name "agger" and instances of the word "Dagger"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cf
    -0.75
     Vide
    -0.72
     Kind
    -0.69
     Surv
    -0.68
     Geo
    -0.65
     Patriarch
    -0.64
     Constantin
    -0.64
    ĻĤ
    -0.62
    ktop
    -0.61
     Occupations
    -0.61
    POSITIVE LOGITS
    agger
    1.35
    uably
    0.87
    mentation
    0.84
    istas
    0.82
    ishly
    0.81
    ashtra
    0.81
    cade
    0.80
    illac
    0.78
    abal
    0.78
    ocity
    0.77
    Activations Density 0.007%

    No Known Activations