INDEX

Explanations

elements related to hypotheses, research design, and experimental conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Personensuche

-0.56

 Мексичка

-0.51

 natin

-0.51

 second

-0.50

 Также

-0.50

verifyException

-0.50

 TAMBIÉN

-0.49

êques

-0.49

 Outro

-0.49

 NDEBUG

-0.49

POSITIVE LOGITS

1.09

1.07

1.05

ⅰ

0.96

⑴

0.87

 Firstly

0.83

 firstly

0.82

㈠

0.81

①

0.80

Activations Density 0.294%

elements related to hypotheses, research design, and experimental conclusions

No Comments

No Known Activations