INDEX

Explanations

references to locations or places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

р

-0.52

存于互联网档案馆

-0.51

 japones

-0.51

 correct

-0.48

put

-0.48

 esame

-0.48

 umum

-0.48

spel

-0.48

agreb

-0.48

ocardio

-0.47

POSITIVE LOGITS

place

1.03

Place

1.02

 Place

0.93

PLACE

0.92

sizeCache

0.87

----</

0.82

OrBuilder

0.78

 advisory

0.76

`{.

0.72

Advisory

0.69

Activations Density 0.113%

references to locations or places

No Comments

No Known Activations