INDEX

Explanations

positive evaluations of dining experiences, particularly regarding prices and food quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

setVerticalGroup

-1.00

RenderAtEndOf

-0.94

UnsafeEnabled

-0.93

mybatisplus

-0.90

AndEndTag

-0.88

ThroughAttribute

-0.87

IntoConstraints

-0.85

ImageContext

-0.85

Geplaatst

-0.84

Jeografia

-0.81

POSITIVE LOGITS

 staff

0.59

<eos>

0.55

0.53

 There

0.49

 nice

0.49

 Staff

0.48

way

0.47

asje

0.45

 cute

0.45

 good

0.45

Activations Density 0.105%

positive evaluations of dining experiences, particularly regarding prices and food quality

No Comments

No Known Activations