INDEX

Explanations

nouns and adjectives describing locations and community attributes

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

-0.91

 виправивши

-0.79

+#+#

-0.69

#+#

-0.66

webElementXpaths

-0.63

\|^{

-0.61

 Мексичка

-0.61

WriteTagHelper

-0.58

tał

-0.57

 MaterialApp

-0.56

POSITIVE LOGITS

 located

1.01

 situated

0.85

 surrounded

0.75

 centrally

0.73

 conveniently

0.69

located

0.68

 privately

0.67

 within

0.66

 connected

0.66

 adjacent

0.66

Activations Density 0.163%

nouns and adjectives describing locations and community attributes

No Comments

No Known Activations