INDEX

Explanations

proper nouns related to names and specific places or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ValueStyle

-0.85

the

-0.66

tales

-0.56

ta

-0.56

-0.54

tone

-0.54

tattoo

-0.53

tum

-0.53

 Paglinawan

-0.52

theatre

-0.50

POSITIVE LOGITS

ses

0.68

ser

0.63

hless

0.60

sing

0.58

hable

0.57

sed

0.57

sy

0.57

sert

0.56

hline

0.54

sie

0.54

Activations Density 0.411%

proper nouns related to names and specific places or entities

No Comments

No Known Activations