INDEX

Explanations

references to specific targets or entities in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

 dysplasia

-0.70

CBA

-0.68

xffffff

-0.67

 fistula

-0.66

Jaz

-0.66

CBA

-0.65

 colitis

-0.63

httphttps

-0.61

writing

-0.60

 gustó

-0.59

POSITIVE LOGITS

 targets

1.83

 target

1.73

 TARGET

1.70

 Target

1.69

 Targets

1.63

TARGET

1.61

target

1.54

Target

1.54

targets

1.53

 cible

1.45

Activations Density 0.083%

references to specific targets or entities in the text

No Comments

No Known Activations