INDEX

Explanations

connectors that indicate relationships or associations between ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 myſelf

-0.98

 themſelves

-0.93

 itſelf

-0.91

 himſelf

-0.89

 whoſe

-0.84

 houſe

-0.84

 ſeveral

-0.83

 ſind

-0.81

ſy

-0.81

 iſt

-0.81

POSITIVE LOGITS

 nakalista

0.61

SourceChecksum

0.58

Loader

0.53

ob

0.49

 HasFactory

0.49

ecuzione

0.49

em

0.48

0.47

ins

0.45

ătate

0.45

Activations Density 0.272%

connectors that indicate relationships or associations between ideas

No Comments

No Known Activations