© 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. 20461
    Prev
    Next
    INDEX
    Explanations

    numerical entities such as numbers and codes

    oai_token-act-pair · gpt-3.5-turbo

    references to formal regulations, amendments, and specific identifiers related to legal or organizational frameworks

    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
    ersive
    -0.67
    leans
    -0.63
    ogging
    -0.62
    assed
    -0.62
    ffen
    -0.61
    resy
    -0.61
    anced
    -0.59
    vernment
    -0.59
     unden
    -0.59
    aps
    -0.59
    POSITIVE LOGITS
     #
    1.25
     No
    1.08
     Nos
    1.05
     XI
    1.03
     XIII
    1.02
     XXX
    1.01
     Number
    1.00
     XIV
    1.00
     XV
    0.96
     00
    0.93
    Activations Density 0.362%

    No Known Activations