INDEX

Explanations

references to experimental results involving rats and summaries of information

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

 Roskov

-0.77

:✨

-0.75

 EconPapers

-0.71

 يتيمه

-0.68

الدراسه

-0.64

ReusableCell

-0.63

 تضيفلها

-0.61

corrência

-0.60

 للمعارف

-0.59

ьаж

-0.58

POSITIVE LOGITS

 summary

0.90

 summarized

0.67

 Plug

0.67

 summar

0.65

 summaries

0.65

 snapshot

0.65

summary

0.65

 plug

0.65

 summarizes

0.62

HashCode

0.61

Activations Density 0.111%

references to experimental results involving rats and summaries of information

No Comments

No Known Activations