INDEX

Explanations

code snippets related to file manipulation and processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

StoryboardSegue

-0.72

脚注の使い方

-0.61

onoi

-0.58

argout

-0.52

toMap

-0.52

 Arboretum

-0.51

 betweenstory

-0.50

punkten

-0.50

Népesség

-0.49

 саны

-0.49

POSITIVE LOGITS

 input

0.60

 Input

0.55

 вход

0.51

 referenties

0.51

 INPUT

0.50

Rüyada

0.50

 ModelExpression

0.50

entrada

0.50

input

0.48

bef

0.48

Activations Density 0.872%

code snippets related to file manipulation and processing

No Comments

No Known Activations