© 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. 2-RES-JB
    11. 4201
    Prev
    Next
    INDEX
    Explanations

    positive attributes or qualities attributed to entities or individuals

    oai_token-act-pair · gpt-3.5-turbo

    words related to qualities and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dos
    -0.76
    analysis
    -0.71
    inav
    -0.67
    NAS
    -0.66
    raid
    -0.64
    MG
    -0.63
    cross
    -0.63
    DO
    -0.63
    space
    -0.62
    carry
    -0.62
    POSITIVE LOGITS
     qualities
    1.11
     traits
    0.96
     virtues
    0.93
     talents
    0.82
     merits
    0.81
    wcsstore
    0.78
     charact
    0.75
     trait
    0.74
    hovah
    0.71
     adject
    0.69
    Activations Density 0.027%

    No Known Activations