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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3358
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a specific person or entity named "Jan"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Jan" or variations related to voting or nominations

    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
    ACTED
    -0.72
     dramatic
    -0.64
     poles
    -0.63
     outgoing
    -0.62
     distributed
    -0.62
     plentiful
    -0.61
     casc
    -0.60
    utenberg
    -0.60
     surviv
    -0.60
     dispersed
    -0.59
    POSITIVE LOGITS
    jan
    1.51
    uary
    1.26
    ovic
    1.09
    vier
    1.04
    ovan
    1.01
    ja
    0.97
    asus
    0.96
    ovi
    0.96
    tenance
    0.89
    jen
    0.88
    Activations Density 0.005%

    No Known Activations