© 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. 10-RES-JB
    11. 21725
    Prev
    Next
    INDEX
    Explanations

    dates and locations or types of events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and their associated names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jian
    -0.97
     PJ
    -0.96
     Connie
    -0.92
    nc
    -0.87
     Julio
    -0.85
     McInt
    -0.84
     Jenn
    -0.83
    NC
    -0.83
     Schne
    -0.83
     Nik
    -0.78
    POSITIVE LOGITS
    land
    1.34
     Land
    1.31
    Land
    1.30
    LAND
    1.26
    lands
    1.19
     Lands
    1.13
     land
    1.06
    658
    1.00
     lands
    0.98
     Landing
    0.95
    Activations Density 0.304%

    No Known Activations