© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 8367
    Prev
    Next
    INDEX
    Explanations

    words related to the process of purification or treatment

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of 'innocence' or 'purity.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     steps
    -0.60
     changes
    -0.57
     grand
    -0.56
     Wo
    -0.56
     changing
    -0.55
     clo
    -0.54
     Ferguson
    -0.54
     boot
    -0.54
    erguson
    -0.53
     Mog
    -0.53
    POSITIVE LOGITS
    inated
    4.32
    inate
    2.76
    inating
    2.73
    inates
    2.68
    ination
    2.55
    inators
    1.86
    inations
    1.85
    inately
    1.77
    inator
    1.73
    inatory
    1.56
    Activations Density 0.009%

    No Known Activations