INDEX

Explanations

references to books and literature-related terminology

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

iyle

-0.53

⁡

-0.50

ところに

-0.49

 fatal

-0.49

GID

-0.48

]--;

-0.46

{{{

-0.46

Keine

-0.45

Dearest

-0.45

hæng

-0.45

POSITIVE LOGITS

helves

0.92

books

0.90

 books

0.88

ends

0.85

worm

0.83

helf

0.82

ended

0.76

 Books

0.75

Books

0.74

marked

0.73

Activations Density 0.096%

references to books and literature-related terminology

No Comments

No Known Activations