INDEX

Explanations

repetitive phrases, particularly those starting with "so."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

μία

-0.79

 hond

-0.72

 vertes

-0.68

indépendance

-0.67

 Winfrey

-0.67

 Achtung

-0.67

Freeman

-0.67

 Breton

-0.66

Gele

-0.65

 Olimpia

-0.65

POSITIVE LOGITS

So

1.44

so

1.38

So

1.35

SO

1.29

so

1.10

Sooo

1.10

Så

1.04

SO

0.98

 sooo

0.97

 sooooo

0.96

Activations Density 0.105%

repetitive phrases, particularly those starting with "so."

No Comments

No Known Activations