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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 2162
    Prev
    Next
    INDEX
    Explanations

    the word "seasoned."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to experience and expertise, particularly those describing individuals proficient in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alter
    -0.98
    otion
    -0.85
    alog
    -0.84
    istics
    -0.80
    phys
    -0.74
    loss
    -0.74
    otions
    -0.72
    matic
    -0.72
    aceae
    -0.71
    plex
    -0.71
    POSITIVE LOGITS
     seasoned
    0.89
     rusty
    0.79
     hardened
    0.77
    ||||
    0.75
     inexper
    0.74
     veteran
    0.73
    ÃįÃį
    0.71
     unprepared
    0.71
     mature
    0.68
     veterans
    0.67
    Activations Density 0.035%

    No Known Activations