INDEX

Explanations

terms related to flags and flag-like constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ymce

-0.89

\"");

-0.84

Daryl

-0.73

."</

-0.72

 Daryl

-0.69

>")

-0.67

)}</

-0.66

 Sims

-0.66

onNext

-0.66

."],

-0.65

POSITIVE LOGITS

 flags

1.85

 FLAG

1.80

 Flags

1.80

 Flag

1.78

 flag

1.69

flag

1.63

FLAG

1.61

flags

1.61

Flags

1.58

 Drapeau

1.54

Activations Density 0.079%

terms related to flags and flag-like constructs

No Comments

No Known Activations