INDEX

Explanations

references to specificity and detail in descriptions

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

 coals

-0.66

onaise

-0.65

Mou

-0.65

 Patro

-0.65

Iva

-0.64

LayoutStyle

-0.64

NTS

-0.64

üyü

-0.63

($__

-0.62

 Clio

-0.61

POSITIVE LOGITS

 specific

1.11

 SPECIFIC

1.06

 Specific

1.04

pecific

1.01

specific

0.99

Specific

0.95

SPECIFIC

0.95

Specifiche

0.94

 spesifik

0.93

ificity

0.91

Activations Density 0.114%

references to specificity and detail in descriptions

No Comments

No Known Activations