© 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. 21737
    Prev
    Next
    INDEX
    Explanations

    quantitative information such as numbers or measurements related to various subjects

    oai_token-act-pair · gpt-3.5-turbo

    metrics related to economic and demographic statistics

    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
    tics
    -0.69
    iate
    -0.68
    mone
    -0.65
    NetMessage
    -0.64
    elight
    -0.61
    vernment
    -0.61
    iates
    -0.60
    olics
    -0.59
    henko
    -0.58
    ascular
    -0.58
    POSITIVE LOGITS
     ranging
    1.31
     exceeding
    1.29
     totaling
    1.20
     averaging
    1.06
     comparable
    1.00
     equivalent
    0.99
     estimated
    0.96
     âī¥
    0.93
     greater
    0.93
     equal
    0.90
    Activations Density 0.167%

    No Known Activations