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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 3273
    Prev
    Next
    INDEX
    Explanations

    phrases related to equalizing or balancing situations

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to equality and fairness in competitive contexts

    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
     nodd
    -0.75
     livest
    -0.64
     contracted
    -0.64
    argon
    -0.63
    agar
    -0.63
     suppressed
    -0.62
    atto
    -0.62
     diction
    -0.60
    owned
    -0.58
    repl
    -0.57
    POSITIVE LOGITS
    izons
    0.83
    enium
    0.80
    ifice
    0.75
    olicy
    0.75
    Enlarge
    0.74
    posts
    0.69
    iday
    0.67
    imen
    0.65
     ahead
    0.65
    ificate
    0.65
    Activations Density 0.153%

    No Known Activations