INDEX

Explanations

complex patterns involving numbers and letters, possibly related to data organization or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 gynhyrchwyd

-0.76

 ویکی‌پدی

-0.75

IUrlHelper

-0.74

клопе

-0.73

 فريبيس

-0.72

éphane

-0.72

úgó

-0.71

ſelf

-0.69

AnimationsModule

-0.69

DoubleQuotes

-0.69

POSITIVE LOGITS

Vidite

0.55

0.53

0.52

0.49

0.48

Morfologia

0.47

помним

0.47

0.46

Activations Density 0.224%

complex patterns involving numbers and letters, possibly related to data organization or identifiers

No Comments

No Known Activations