© 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
    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. 24170
    Prev
    Next
    INDEX
    Explanations

    mentions of anthropology-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to anthropology and its subfields

    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
    Tube
    -0.81
    FUL
    -0.70
    HCR
    -0.70
    VK
    -0.69
    LOAD
    -0.68
    20439
    -0.67
    DAQ
    -0.67
     Grind
    -0.66
    916
    -0.66
     Pharmaceutical
    -0.65
    POSITIVE LOGITS
    omorphic
    1.21
     anthrop
    1.14
    omorph
    1.13
    ologist
    1.00
    anthrop
    0.99
    ologists
    0.98
    ological
    0.97
     Anthrop
    0.95
    istic
    0.90
     anthropology
    0.90
    Activations Density 0.013%

    No Known Activations