INDEX

Explanations

words related to sheets or shadows in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Efq

-0.97

 Shakspeare

-0.91

 blessés

-0.89

 mourut

-0.85

 ་་

-0.85

 enfans

-0.83

 photolibrary

-0.81

mybatisplus

-0.81

 prisonniers

-0.81

 feminina

-0.81

POSITIVE LOGITS

ha

0.71

Things

0.71

 things

0.69

0.65

things

0.64

0.63

 Things

0.59

now

0.57

 functions

0.56

↵

0.56

Activations Density 0.198%

words related to sheets or shadows in various contexts

No Comments

No Known Activations