© 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. 9-RES-JB
    11. 8829
    Prev
    Next
    INDEX
    Explanations

    adjectives related to a high level of significance or intensity

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to significant events, transformations, or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dialogue
    -0.78
    ossier
    -0.76
    akeru
    -0.68
    podcast
    -0.67
     CoC
    -0.66
    atform
    -0.65
    izza
    -0.63
    partisan
    -0.63
     Franch
    -0.63
    amera
    -0.60
    POSITIVE LOGITS
     electrons
    0.77
    assic
    0.75
    obyl
    0.71
    glers
    0.71
    ochemical
    0.67
    uristic
    0.65
     enzymes
    0.65
    Chem
    0.64
    cific
    0.64
     hazard
    0.63
    Activations Density 1.040%

    No Known Activations