© 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. 10-RES-JB
    11. 13874
    Prev
    Next
    INDEX
    Explanations

    words related to locations and events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spirit and community actions in various contexts

    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
    ãĥĻ
    -0.58
    essor
    -0.55
    pires
    -0.51
    pired
    -0.50
    )\
    -0.49
    ãĥĩãĤ£
    -0.49
    amy
    -0.49
    ãĥĬ
    -0.47
    anooga
    -0.47
    pressed
    -0.47
    POSITIVE LOGITS
     because
    1.23
     whilst
    1.13
     when
    1.09
     during
    1.06
     until
    1.06
     shortly
    1.04
     although
    1.03
     while
    1.01
     due
    1.00
     since
    0.99
    Activations Density 1.202%

    No Known Activations