INDEX

Explanations

references to various types of activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

받

-0.82

 cuánt

-0.77

 Mende

-0.69

 Gers

-0.67

받

-0.67

 forgiving

-0.66

jsonwebtoken

-0.66

Zal

-0.63

Zal

-0.62

ranes

-0.62

POSITIVE LOGITS

 activity

2.42

 activities

2.41

 Activity

2.13

 Activities

2.12

activities

2.10

Activity

2.06

activity

2.01

Activities

2.01

 ACTIVITY

2.00

 activités

1.92

Activations Density 0.064%

references to various types of activities

No Comments

No Known Activations