© 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. 8-RES-JB
    11. 2405
    Prev
    Next
    INDEX
    Explanations

    terms related to describing and analyzing characteristics or qualities of entities

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with characterization and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EMS
    -0.79
    yg
    -0.74
    algia
    -0.72
    VEN
    -0.68
    gard
    -0.67
    IDA
    -0.65
    abouts
    -0.64
    scl
    -0.64
    chedel
    -0.62
    habi
    -0.61
    POSITIVE LOGITS
    istically
    1.58
    istics
    1.57
    izations
    1.37
    izes
    1.20
    isations
    1.09
    isation
    1.07
     assassination
    1.06
    ised
    0.99
    acters
    0.98
    izing
    0.97
    Activations Density 0.033%

    No Known Activations