INDEX

Explanations

phrases and actions that indicate making a point or highlighting something

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

NewReader

-0.59

 Either

-0.58

ranging

-0.53

 оригіналу

-0.53

Either

-0.53

!("{}",

-0.51

pede

-0.50

gir

-0.50

ariales

-0.49

tiges

-0.49

POSITIVE LOGITS

 souligné

0.84

 señalar

0.79

 segnal

0.77

 pointed

0.76

 remarquer

0.75

 remarqué

0.75

 noted

0.74

 noticed

0.74

 soulign

0.72

 отметить

0.71

Activations Density 0.357%

phrases and actions that indicate making a point or highlighting something

No Comments

No Known Activations