INDEX

Explanations

concepts related to hiding or storing items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 مشين

-0.67

RectangleBorder

-0.61



-0.60

 distanciation

-0.60

ftagPool

-0.59

STRONG

-0.57

ọi

-0.55

 GetEnumerator

-0.54

 nakalista

-0.54

scn

-0.52

POSITIVE LOGITS

 tucked

1.17

 tuck

1.10

Tuck

1.03

 concealment

1.02

 Tuck

1.02

 hiding

1.00

 concealed

0.97

 hidden

0.93

 concealing

0.89

 stored

0.87

Activations Density 0.414%

concepts related to hiding or storing items

No Comments

No Known Activations