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. 4-RES-JB
    6. 5763
    Prev
    Next
    INDEX
    Explanations

    specific terms related to appointments or designations of individuals to certain roles or positions

    oai_token-act-pair · gpt-3.5-turbo

    words related to appointments or designations in various contexts

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

    No Comments

    Negative Logits
    matically
    -0.76
    zee
    -0.74
    zees
    -0.70
    houses
    -0.68
    matic
    -0.68
    crow
    -0.67
    HB
    -0.67
    enstein
    -0.66
    java
    -0.65
    icides
    -0.63
    POSITIVE LOGITS
    ointed
    0.82
     conduc
    0.80
    ourn
    0.77
    semble
    0.72
     bargain
    0.70
    inez
    0.69
    DCS
    0.69
    ados
    0.67
    icion
    0.67
    STRUCT
    0.65
    Activations Density 0.032%

    No Known Activations