INDEX

Explanations

references to user-related entities and their attributes in the code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Stopwatch

-0.90

 ProductService

-0.85

 combineReducers

-0.81

glEnd

-0.77

 ApiService

-0.74

 snippetHide

-0.72

CrossRef

-0.71

PSM

-0.71

 Amiens

-0.71

PRD

-0.70

POSITIVE LOGITS

 Users

1.21

 users

1.17

 USER

1.16

 User

1.11

 user

1.10

users

1.03

 USERS

0.98

USER

0.97

Users

0.97

user

0.94

Activations Density 0.041%

references to user-related entities and their attributes in the code

No Comments

No Known Activations