INDEX

Explanations

dynamic verbs and adjectives that indicate significant changes or movements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 TABLE

-0.62

之

-0.61

 Goodwin

-0.60

 table

-0.58

ube

-0.58

 Interess

-0.56

sup

-0.54

 cons

-0.54

 comprim

-0.54

âm

-0.54

POSITIVE LOGITS

 seamlessly

1.00

 ſon

0.91

 flawlessly

0.89

 sparked

0.87

 decisivo

0.86

theless

0.86

 clinched

0.85

MigrationBuilder

0.84

 glimpses

0.84

Portail

0.84

Activations Density 0.238%

dynamic verbs and adjectives that indicate significant changes or movements

No Comments

No Known Activations