INDEX

Explanations

expressions of uncertainty or subjective perception

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

to seem or appear

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

Negative Logits

 gezet

-0.48

edicated

-0.43

 את

-0.43

возь

-0.41

thang

-0.41

XmlEnum

-0.40

pur

-0.40

Portail

-0.39

EXE

-0.39

NIC

-0.38

POSITIVE LOGITS

 parezca

0.83

 Parece

0.83

 parecer

0.82

Parece

0.82

 parecía

0.81

 parecen

0.79

 parece

0.78

 seem

0.77

 paraître

0.75

 Seem

0.71

Activations Density 0.030%

expressions of uncertainty or subjective perception

to seem or appear

No Known Activations