INDEX

Explanations

terms related to formal processes and arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

par

-0.45

 lệ

-0.43

 wide

-0.39

ต

-0.39

 "..\..\..\

-0.39

 "..\..\

-0.39

Par

-0.39

 раз

-0.38

 ей

-0.37

żer

-0.36

POSITIVE LOGITS

 myſelf

0.80

 Anſ

0.78

 Descartes

0.77

Efq

0.76

 BoxFit

0.76

 ་་

0.76

 doubtnut

0.75

CppCodeGen

0.74

ſelves

0.73

ſelf

0.72

Activations Density 1.085%

terms related to formal processes and arguments

No Comments

No Known Activations