INDEX

Explanations

expressions of opinion or subjective evaluations

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

preceding or describing auditory impressions

np_acts-logits-general · gemini-2.0-flash

sounds like, looks like

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 houſe

-0.68

 Majefty

-0.67

 ſtate

-0.61

 CanadaChoose

-0.60

 Chriftian

-0.58

 Jefus

-0.58

tersebut

-0.58

NewGuid

-0.58

 riks

-0.57

buttonShape

-0.56

POSITIVE LOGITS

 quite

0.79

 pretty

0.72

 like

0.68

 very

0.65

 >=",

0.59

 promising

0.56

BarStyle

0.56

 saites

0.55

 rather

0.55

 fairly

0.54

Activations Density 0.118%

expressions of opinion or subjective evaluations

preceding or describing auditory impressions

sounds like, looks like

No Comments

No Known Activations