INDEX

Explanations

terms related to receiving or accepting treatment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 calendriers

-0.83

存于互联网档案馆

-0.80

 Insee

-0.73

 חיצוניים

-0.71

ysław

-0.71

tonsoft

-0.68

 reft

-0.68

яза

-0.67

GraphicsUnit

-0.66

insee

-0.66

POSITIVE LOGITS

 receive

0.73

 RECEIVE

0.71

 Receive

0.71

 receives

0.69

 RECE

0.67

RECE

0.64

RECEIVE

0.62

 recieve

0.61

 Receives

0.60

 Reception

0.58

Activations Density 0.091%

terms related to receiving or accepting treatment

No Comments

No Known Activations