INDEX

Explanations

references to a "target" or related terminology in a technical or scientific context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CBA

-0.70

 CGFloat

-0.67

 fistula

-0.65

CBA

-0.64

 companyId

-0.62

xffffff

-0.62

 FLOW

-0.60

 vroe

-0.59

 colitis

-0.59

Simmons

-0.59

POSITIVE LOGITS

 targets

2.44

 target

2.40

 Target

2.26

 TARGET

2.24

 Targets

2.17

target

2.15

TARGET

2.14

Target

2.13

targets

1.99

 cible

1.93

Activations Density 0.058%

references to a "target" or related terminology in a technical or scientific context

No Comments

No Known Activations