INDEX

Explanations

instances of negative framing in research contexts

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

however but thus

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

endphp

-0.66

GEBURTSDATUM

-0.65

 TextAlign

-0.62

ExtendWith

-0.60

⭗

-0.59

WireFormatLite

-0.59

 パンチラ

-0.59

𑄮

-0.59

[@BOS@]

-0.58

<unused11>

-0.58

POSITIVE LOGITS

 mało

0.23

 Perlu

0.23

 belki

0.23

&-

0.21

 radically

0.20

 kän

0.20

Introducción

0.20

<strong>

0.20

fromnode

0.20

 metodología

0.20

Activations Density 0.079%

instances of negative framing in research contexts

however but thus

No Comments

No Known Activations