Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 8913
    Prev
    Next
    INDEX
    Explanations

    words and punctuation that indicate continuity or connection in a sentence or thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.07
    2:0.07
    3:0.08
    4:0.09
    5:0.10
    6:0.08
    7:0.08
    8:0.08
    9:0.06
    10:0.09
    11:0.08
    Negative Logits
     prejudice
    -2.30
     misunder
    -2.12
     GOODMAN
    -2.11
     sugg
    -2.08
     strugg
    -2.05
     describ
    -2.02
    recomm
    -2.01
     mathemat
    -2.00
    Cooldown
    -1.94
     dusk
    -1.94
    POSITIVE LOGITS
     Hulk
    2.27
     \"
    2.25
     (_
    2.08
    ria
    2.03
    rite
    2.00
     Leilan
    1.99
    idia
    1.97
    rote
    1.91
     ({
    1.89
    Ghost
    1.89
    Activations Density 0.000%

    No Known Activations