INDEX

Explanations

expressions of disbelief or incredulity in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Follows words indicating doubt or disbelief

np_acts-logits-general · gemini-2.0-flash

unexpectedly would

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AddHtmlAttribute

-0.63

'])->

-0.59

'][]

-0.58

Personendaten

-0.55

 insuffisamment

-0.55

}}]{

-0.53

Jeografia

-0.51

}}],

-0.51

windowFixed

-0.50

 refirió

-0.50

POSITIVE LOGITS

竟然

0.82

竟

0.75

 such

0.72

居然

0.70

 solch

0.70

 anyone

0.69

 anybody

0.65

 چنین

0.65

竟然是

0.63

such

0.63

Activations Density 0.221%

expressions of disbelief or incredulity in various contexts

Follows words indicating doubt or disbelief

unexpectedly would

No Comments

No Known Activations