INDEX

Explanations

names and titles in a legal or formal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

his

-0.79

 himself

-0.76

 kanyang

-0.71

himself

-0.70

 seinem

-0.69

 själv

-0.67

 distanciation

-0.66

 magát

-0.64

 ThemeData

-0.61

 seinen

-0.59

POSITIVE LOGITS

 themselves

1.75

 their

1.65

Their

1.65

 Their

1.54

their

1.54

themselves

1.37

 THEIR

1.26

 deres

1.26

他们的

1.09

eds

1.07

Activations Density 0.776%

names and titles in a legal or formal context

No Comments

No Known Activations