INDEX

Explanations

references to storytelling or narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Félix

-0.78

人民共和国

-0.77

principalColumn

-0.75

 velours

-0.74

##############

-0.68

cstdlib

-0.68

 سكانية

-0.68

ihnachten

-0.68

ภัณฑ์

-0.67

bbene

-0.66

POSITIVE LOGITS

 story

2.42

 stories

2.26

 Story

2.17

Story

2.06

story

2.05

 STORY

1.99

 Stories

1.94

Stories

1.86

stories

1.75

STORY

1.73

Activations Density 0.032%

references to storytelling or narratives

No Comments

No Known Activations