INDEX

Explanations

words and phrases emphasizing clarity and specificity in communication

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

tvguidetime

-0.88

ReusableCell

-0.87

+#+#

-0.86

 snippetHide

-0.80

 tartalomajánló

-0.77

 "..\..\..\

-0.73

bkz

-0.68

 "..\..\

-0.66

sizeCache

-0.65

 мәкал

-0.64

POSITIVE LOGITS

 Surround

0.63

 surroundings

0.62

Географиясе

0.59

 Rahmen

0.55

 explicit

0.55

 birthday

0.54

 surround

0.53

 surrounds

0.53

Bounds

0.52

Према

0.52

Activations Density 0.141%

words and phrases emphasizing clarity and specificity in communication

No Comments

No Known Activations