© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 46000
    Prev
    Next
    INDEX
    Explanations

    various forms of the letter 's'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.16
    1:0.15
    2:0.13
    3:0.03
    4:0.03
    5:0.19
    6:0.09
    7:0.01
    8:0.02
    9:0.04
    10:0.04
    11:0.07
    Negative Logits
    fax
    -1.99
    ynchronous
    -1.92
    wash
    -1.89
    scroll
    -1.80
    ay
    -1.70
    ync
    -1.69
    catch
    -1.68
    fortunately
    -1.67
    Wan
    -1.67
    rame
    -1.65
    POSITIVE LOGITS
    senal
    2.18
     hegemony
    1.82
     propensity
    1.73
     acknowled
    1.72
     workforce
    1.68
     playbook
    1.66
     branding
    1.64
     CoC
    1.64
     affinity
    1.62
     supra
    1.60
    Activations Density 0.138%

    No Known Activations