INDEX

Explanations

text related to physical locations and movements within a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

mergeFrom

-0.64

ictwa

-0.55

phemy

-0.55

ctuaries

-0.53

Geplaatst

-0.52

liothèque

-0.51

Vidite

-0.51

miques

-0.51

itettura

-0.48

yorsunuz

-0.48

POSITIVE LOGITS

 front

0.71

 lenker

0.62

 المعيارى

0.61

 nearest

0.60

 floor

0.59

 window

0.58

&[

0.57

 rear

0.57

front

0.56

Skocz

0.56

Activations Density 0.271%

text related to physical locations and movements within a narrative context

No Comments

No Known Activations