INDEX

Explanations

names of individuals, particularly in celebrity or public contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gameserver

-0.55

 BadRequest

-0.52

dropna

-0.51

 вікі

-0.49

 pomen

-0.49

 Beecher

-0.48

splitlines

-0.47

lineTo

-0.46

 prisonniers

-0.46

 darb

-0.46

POSITIVE LOGITS

✨:

0.72

̓

0.69

iteit

0.66

antly

0.66

__))

0.64

ividual

0.61

argout

0.61

")){

0.61

uação

0.60

--}}

0.60

Activations Density 0.111%

names of individuals, particularly in celebrity or public contexts

No Comments

No Known Activations