INDEX

Explanations

references to locations and movement within them

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

"the" followed by a location

np_acts-logits-general · gemini-2.0-flash

places and environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

SequentialGroup

-0.71

 coasts

-0.61

 simplifié

-0.60

 shores

-0.59

rungsseite

-0.58

 coast

-0.56

norr

-0.56

 surfaces

-0.55

 occa

-0.53

 måde

-0.52

POSITIVE LOGITS

 midst

0.79

 woods

0.72

 '\\;'

0.66

KommentareTeilen

0.65

psack

0.61

PRNewswire

0.54

 thro

0.53

 bushes

0.53

providedIn

0.52

 yard

0.52

Activations Density 0.267%

references to locations and movement within them

"the" followed by a location

places and environments

No Comments

No Known Activations