INDEX

Explanations

phrases that express a sense of reduction or decrease

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

DockStyle

-0.77

skosten

-0.74

bingen

-0.72

 CarPlay

-0.71

‍♀️

-0.71

 BoxDecoration

-0.71

Wib

-0.70

harusnya

-0.70

 Kirkwood

-0.69

 conviene

-0.69

POSITIVE LOGITS

 less

1.48

 LESS

1.45

 Less

1.39

Less

1.36

less

1.22

 Lessing

1.13

LESS

1.13

 moins

1.05

 menos

1.04

 lefs

0.96

Activations Density 0.101%

phrases that express a sense of reduction or decrease

No Comments

No Known Activations