INDEX

Explanations

occurrences of the word "the"

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

Followed by "alternative"

np_acts-logits-general · gemini-2.0-flash

alternative to

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

Jîn

-0.56

 ymin

-0.55

кість

-0.55

 Wikimédia

-0.54

UnknownFieldSet

-0.54

 Gonna

-0.53

 newName

-0.53

gonna

-0.53

χή

-0.52

 nông

-0.51

POSITIVE LOGITS

 متعلقه

0.74

Билгалдахарш

0.68

'],

0.66

ViewFeatures

0.66

'])

0.64

Lähteet

0.62

TestTools

0.61

'];

0.61

expandindo

0.61

Referanser

0.59

Activations Density 0.473%

occurrences of the word "the"

Followed by "alternative"

alternative to

No Comments

No Known Activations