INDEX

Explanations

terms related to requests and seeking approval or assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Roskov

-1.03

-0.78

 ویکی‌پدیا

-0.72

AutoScaleMode

-0.71

WithIOException

-0.70

 مشين

-0.68

Gön

-0.65

 ويكيپيديا

-0.64

ⓘ

-0.62

Havolalar

-0.62

POSITIVE LOGITS

 answers

1.02

 clarification

0.99

 redress

0.79

 revenge

0.76

 explanations

0.76

 attention

0.75

 ANSWERS

0.74

 permission

0.74

 Answers

0.72

 explanation

0.72

Activations Density 0.350%

terms related to requests and seeking approval or assistance

No Comments

No Known Activations