INDEX

Explanations

references to similarity or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

es

-0.60

cupa

-0.59

Azz

-0.52

 sphinct

-0.50

ste

-0.50

onso

-0.50

Dens

-0.50

voz

-0.49

 ulang

-0.49

𝐟

-0.48

POSITIVE LOGITS

RectangleBorder

1.25

 nahilalakip

1.08

 BoxFit

1.00

iliar

0.89

 SIMILAR

0.89

RenderAtEndOf

0.88

rrggbb

0.87

 sims

0.87

pexpr

0.87

 فريبيس

0.86

Activations Density 0.146%

references to similarity or comparisons

No Comments

No Known Activations