© 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. 0-RES-JB
    11. 13965
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific brand or product line

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the term "OG" or its variations, indicating a focus on specific subjects or entities characterized by that term

    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
     Dracula
    -0.70
     succ
    -0.66
     dared
    -0.66
     insur
    -0.62
     jan
    -0.60
    uthor
    -0.59
     Ces
    -0.59
     "$:/
    -0.59
     Civil
    -0.58
     Harris
    -0.58
    POSITIVE LOGITS
    OG
    4.20
    ogs
    1.78
    og
    1.67
    OGR
    1.58
    OD
    1.51
    OLOG
    1.48
    OC
    1.45
    OB
    1.44
    ogg
    1.36
    UG
    1.34
    Activations Density 0.012%

    No Known Activations