INDEX

Explanations

terms associated with impact and influence in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Huxley

-0.53

сихо

-0.51

-0.50

初め

-0.49

 utilizzare

-0.49

айт

-0.49

-0.47

pa

-0.47

POSITIVE LOGITS

 snippetHide

0.95

WriteTagHelper

0.95

 influencing

0.91

 affecting

0.90

 beginnetje

0.88

 insuffisamment

0.87

 utafitiHapana

0.87

 impacting

0.86

affect

0.85

 affect

0.85

Activations Density 0.305%

terms associated with impact and influence in various contexts

No Comments

No Known Activations