INDEX

Explanations

phrases focused on searching for solutions and new ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

AddTagHelper

-0.78

twimg

-0.67

PerformLayout

-0.64

WithMany

-0.62

CppCodeGen

-0.61

Autoritní

-0.61

principalTable

-0.54

 citada

-0.52

 gewüns

-0.51

ciating

-0.51

POSITIVE LOGITS

 ways

2.73

 Ways

1.94

 WAYS

1.87

Ways

1.81

ways

1.73

 methods

1.67

 maneras

1.58

 maneiras

1.57

WAYS

1.43

 способы

1.39

Activations Density 0.529%

phrases focused on searching for solutions and new ideas

No Comments

No Known Activations