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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3048
    Prev
    Next
    INDEX
    Explanations

    phrases related to inclusivity or general statements about groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people or entities

    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
    itta
    -0.72
    odcast
    -0.70
    edia
    -0.67
    tch
    -0.64
    instein
    -0.62
    iceps
    -0.61
    addafi
    -0.61
    osate
    -0.61
    senal
    -0.60
    ello
    -0.60
    POSITIVE LOGITS
     except
    1.47
     imaginable
    1.07
     alike
    1.06
     whatsoever
    1.05
    except
    1.04
    soever
    0.99
     irrespective
    0.91
     facets
    0.88
     regardless
    0.79
     thereafter
    0.78
    Activations Density 0.207%

    No Known Activations