INDEX

Explanations

references to legal procedures and decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

tagHelperRunner

-0.80

 esternos

-0.71

RepeatedField

-0.71

RenderAtEndOf

-0.69

StructEnd

-0.64

 ujednoznacz

-0.63

 defaultstate

-0.62

LookAnd

-0.61

ValueStyle

-0.60

CloseOperation

-0.60

POSITIVE LOGITS

 appropriate

1.30

appropriate

1.08

 justified

1.06

 advisable

1.05

 sensible

1.05

 wise

1.03

 justifiable

1.03

 logical

1.02

 desirable

1.01

Appropriate

1.00

Activations Density 0.635%

references to legal procedures and decision-making

No Comments

No Known Activations