INDEX

Explanations

mentions of inner and outer as descriptors 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 @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Wiktionnaire

-0.82

parsedMessage

-0.80

出版年

-0.77

 يتيمه

-0.70

Personensuche

-0.69

 <=",

-0.67

 الحره

-0.67

#+#

-0.67

 AssemblyCulture

-0.67

oredCriteria

-0.64

POSITIVE LOGITS

most

0.84

MOST

0.80

 most

0.74

 layer

0.70

 layers

0.64

 core

0.61

 periphery

0.61

Most

0.61

 MOST

0.60

 OUTER

0.59

Activations Density 0.087%

mentions of inner and outer as descriptors in various contexts

No Comments

No Known Activations