© 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. 7-RES-JB
    11. 20006
    Prev
    Next
    INDEX
    Explanations

    terms related to the field of anthropology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to anthropology and anthropological studies

    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
    DAQ
    -0.78
    Tube
    -0.73
    Deal
    -0.69
     Stra
    -0.68
    VK
    -0.67
    LOAD
    -0.65
     Shades
    -0.64
    FUL
    -0.64
     Madden
    -0.64
     Stall
    -0.64
    POSITIVE LOGITS
    omorphic
    1.37
    omorph
    1.20
    ological
    1.19
    ologist
    1.19
    ologists
    1.15
    anthrop
    1.08
    ogenic
    1.08
    ocene
    1.05
    ocent
    1.03
    alog
    1.03
    Activations Density 0.024%

    No Known Activations