© 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. 1-RES-JB
    11. 10442
    Prev
    Next
    INDEX
    Explanations

    numerical values that are specified as being approximate or around a specific number

    oai_token-act-pair · gpt-3.5-turbo

    expressions of approximation or estimation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enders
    -0.82
    ieu
    -0.79
    iled
    -0.76
    hered
    -0.74
    oli
    -0.72
    Express
    -0.70
    woods
    -0.69
    olog
    -0.69
    zzle
    -0.68
    actic
    -0.67
    POSITIVE LOGITS
    Ĥİ
    1.03
     approximately
    0.85
    approximately
    0.80
     eleph
    0.77
     Approximately
    0.77
     approximate
    0.76
     (~
    0.75
    atility
    0.73
     800
    0.72
    ©¶æ
    0.72
    Activations Density 0.007%

    No Known Activations