INDEX

Explanations

questions, particularly those starting with "why."

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

Datuak

-0.79

 AssemblyCompany

-0.76

httphttps

-0.74

UserScript

-0.73

 noqa

-0.70

ecap

-0.69

elemField

-0.67

UIControlState

-0.67

دانشنامهٔ

-0.66

mybatisplus

-0.66

POSITIVE LOGITS

 aren

0.86

 didn

0.82

 shouldn

0.80

 else

0.79

 wouldn

0.78

 exactly

0.78

don

0.76

 couldn

0.75

 would

0.73

isn

0.73

Activations Density 0.031%

questions, particularly those starting with "why."

No Comments

No Known Activations