INDEX

Explanations

phrases indicating importance or significance

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

aarrggbb

-0.54

antMatchers

-0.53

もしれない

-0.51

mba

-0.49

 rato

-0.48

aba

-0.48

 next

-0.47

next

-0.46

 Haas

-0.45

わる

-0.44

POSITIVE LOGITS

tvguidetime

0.88

0.80

 AttributeSet

0.79

+#+

0.77

 Infórmanos

0.77

EndGlobalSection

0.71

AddTagHelper

0.70

findpost

0.70

SizeF

0.69

Kanpo

0.68

Activations Density 0.803%

phrases indicating importance or significance

No Known Activations