INDEX

Explanations

references to text message content and formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 تضيفلها

-1.15

 للاسماء

-1.11

 ligiloj

-1.09

IsPostBack

-1.06

 poffible

-1.06

 ostavi

-1.04

Pranala

-1.02

SBATCH

-1.01

 يتيمه

-1.01

Efq

-0.99

POSITIVE LOGITS

 text

1.90

 Text

1.77

text

1.75

 TEXT

1.66

TEXT

1.63

Text

1.58

 texts

1.50

 setText

1.18

 Texts

1.16

 texte

1.15

Activations Density 0.071%

references to text message content and formats

No Comments

No Known Activations