INDEX

Explanations

the word "Given" in various contexts, often indicating a premise or condition in a statement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-1.26

 itſelf

-1.19

 Theſe

-1.17

 houſe

-1.15

 whoſe

-1.12

 ſtate

-1.06

 Reſ

-1.05

 Beſ

-1.03

 greateſt

-1.03

 ſever

-1.02

POSITIVE LOGITS

ed

0.79

Given

0.67

 Given

0.67

Ed

0.61

Ed

0.57

timewa

0.56

ed

0.56

 transfieras

0.56

 Went

0.56

 went

0.56

Activations Density 0.124%

the word "Given" in various contexts, often indicating a premise or condition in a statement

No Comments

No Known Activations