© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 3721
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific last name, "Hollins"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual named Hollins

    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
    ãĥ¥
    -0.72
    PDATE
    -0.71
     schizophrenia
    -0.65
     depression
    -0.61
    resents
    -0.60
    ãĥ£
    -0.60
     saline
    -0.59
     sensitivity
    -0.59
     metals
    -0.59
    ulously
    -0.58
    POSITIVE LOGITS
    iday
    1.28
    idays
    1.18
    inger
    1.05
    aday
    0.95
    ieu
    0.92
    wich
    0.91
    ipop
    0.90
    inson
    0.90
    ippi
    0.88
    enberg
    0.88
    Activations Density 0.006%

    No Known Activations