INDEX

Explanations

references to authority or commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

UnknownFieldSet

-0.82

DataAnnotations

-0.77

 Monfieur

-0.74

 AssemblyTitle

-0.74

 greateſt

-0.73

 Apertura

-0.72

 Chriſt

-0.71

gridx

-0.71

ImageContext

-0.70

lename

-0.70

POSITIVE LOGITS

có

0.73

要

0.71

 phải

0.71

有

0.70

 vouloir

0.68

能

0.67

 Puede

0.66

有

0.66

be

0.66

可

0.62

Activations Density 0.030%

references to authority or commands

No Comments

No Known Activations