© 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. 4-RES-JB
    11. 20350
    Prev
    Next
    INDEX
    Explanations

    references to remembering or recalling information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the act of recalling or referring to previous information

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

    No Comments

    Negative Logits
    managed
    -0.73
     handlers
    -0.62
    CG
    -0.62
    Used
    -0.61
     upkeep
    -0.60
     catering
    -0.60
     disappeared
    -0.59
    onna
    -0.59
    PAC
    -0.58
    Vs
    -0.58
    POSITIVE LOGITS
     summarize
    0.84
    odox
    0.81
    lege
    0.78
     caveats
    0.77
     empir
    0.76
     hypot
    0.75
     Explain
    0.75
    iris
    0.73
     conclusions
    0.72
     Facts
    0.72
    Activations Density 0.898%

    No Known Activations