© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23361
    Prev
    Next
    INDEX
    Explanations

    keywords related to actions of recovery or reversal

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "backs," indicating a focus on various types of returns or recoveries in different contexts

    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
    ITE
    -0.68
     medium
    -0.65
     degree
    -0.61
     plural
    -0.60
     mur
    -0.60
     dose
    -0.59
     princip
    -0.59
     Mash
    -0.58
     cause
    -0.57
     IC
    -0.57
    POSITIVE LOGITS
    backs
    4.73
    back
    2.83
    BACK
    2.12
     backs
    1.77
    downs
    1.40
    Back
    1.33
    backer
    1.31
    aways
    1.30
    outs
    1.21
    offs
    1.15
    Activations Density 0.011%

    No Known Activations