INDEX

Explanations

expressions of uncertainty or speculation

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

expressing probability

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 dép

-0.53

mær

-0.52

 betweenstory

-0.51

Witam

-0.48

antMatchers

-0.47

RenderAtEndOf

-0.47

IFICATE

-0.47

 ligiloj

-0.46

 hjelp

-0.45

 faſt

-0.45

POSITIVE LOGITS

Probably

0.98

 Probably

0.96

 probably

0.85

probably

0.84

mutlich

0.71

 prolly

0.71

 probable

0.62

 waarschijnlijk

0.60

Possibly

0.59

 likely

0.59

Activations Density 0.016%

expressions of uncertainty or speculation

expressing probability

No Comments

No Known Activations

expressions of uncertainty or speculation

expressing probability

No Comments

No Known Activations