INDEX

Explanations

verbs and actions indicating influence or contribution

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

 Myself

-0.74

 Yourself

-0.71

myself

-0.68

########.

-0.65

onAttach

-0.65

 myself

-0.64

 yourselves

-0.63

Myself

-0.63

yourself

-0.62

expandindo

-0.62

POSITIVE LOGITS

 itself

0.71

 both

0.62

 nicely

0.60

us

0.60

 many

0.58

our

0.53

itself

0.53

the

0.53

かえ

0.52

 tremendously

0.52

Activations Density 0.504%

verbs and actions indicating influence or contribution

No Comments

No Known Activations