INDEX

Explanations

words related to hiding or concealing information or objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

AdapterView

-0.73

MigrationBuilder

-0.73

WithFormat

-0.65

CWE

-0.63

 onResponse

-0.63

 strokes

-0.63

 }}">

-0.61

="#">

-0.60

SIA

-0.59

<em>

-0.58

POSITIVE LOGITS

 hiding

1.21

 hide

1.20

 hides

1.18

hiding

1.16

 Hidden

1.15

hid

1.13

 Hiding

1.12

 Hide

1.09

HIDDEN

1.07

 hidden

1.06

Activations Density 0.095%

words related to hiding or concealing information or objects

No Comments

No Known Activations