INDEX

Explanations

occurrences of variable or index references within arrays or lists

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

 tham

-0.48

 Brou

-0.47

RuntimeObject

-0.47

 sista

-0.46

men

-0.45

 крайней

-0.45

 conditionally

-0.45

mtable

-0.44

 ausge

-0.44

 temporarily

-0.44

POSITIVE LOGITS

 index

0.96

 Seating

0.89

 linkovi

0.87

 Index

0.87

 seating

0.82

+#+#

0.82

BeginContext

0.81

enumi

0.81

NUMX

0.78

ArgsConstructor

0.77

Activations Density 0.139%

occurrences of variable or index references within arrays or lists

No Comments

No Known Activations