INDEX

Explanations

instances of the first-person pronoun "I" and associated personal affirmations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ArgsConstructor

-0.67

 <=",

-0.62

BASEPATH

-0.60

 referenties

-0.57

protoimpl

-0.57

RegressionTest

-0.56

клопе

-0.56

ngrx

-0.55

 ويكيميديا

-0.54

thâu

-0.54

POSITIVE LOGITS

 disagrees

0.72

 objected

0.71

 dénon

0.71

 objection

0.66

 appalled

0.65

 refute

0.65

 rebuke

0.64

 object

0.64

 disagreed

0.63

 disagree

0.63

Activations Density 0.291%

instances of the first-person pronoun "I" and associated personal affirmations

No Known Activations