© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43227
    Prev
    Next
    INDEX
    Explanations

    references to progress or forward movement in various contexts

    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
    0:0.01
    1:0.01
    2:0.12
    3:0.10
    4:0.24
    5:0.04
    6:0.07
    7:0.08
    8:0.05
    9:0.04
    10:0.12
    11:0.08
    Negative Logits
     sucker
    -1.51
    cart
    -1.30
     crap
    -1.25
     flee
    -1.24
     punched
    -1.23
    Hz
    -1.21
     float
    -1.20
    wered
    -1.19
     Bethlehem
    -1.19
    perties
    -1.18
    POSITIVE LOGITS
    ��
    1.67
    uesday
    1.63
    TION
    1.62
     sugg
    1.57
    nesday
    1.52
     GOODMAN
    1.51
     newfound
    1.46
    swe
    1.46
    ISSION
    1.42
    OLOGY
    1.41
    Activations Density 0.003%

    No Known Activations