INDEX

Explanations

boolean expressions indicating truth values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 gồm

-0.50

 degli

-0.45

 متعلقه

-0.45

()}>

-0.45

multi

-0.44

itosti

-0.44

いていた

-0.44

なんだろう

-0.44

about

-0.44

sság

-0.43

POSITIVE LOGITS

 true

1.09

true

1.09

 False

1.05

 True

0.97

stdbool

0.96

 TRUE

0.92

 false

0.90

False

0.87

TRUE

0.85

True

0.84

Activations Density 0.135%

boolean expressions indicating truth values

No Comments

No Known Activations