INDEX

Explanations

terms related to collections and colors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

joje

-0.47

 superiore

-0.46

lu

-0.46

 đó

-0.45

 extra

-0.44

ru

-0.44

 obstante

-0.44

el

-0.42

POSITIVE LOGITS

 Colors

1.54

Colors

1.30

 Colours

1.25

 COLORS

1.20

 colors

1.19

colors

1.15

 colours

1.09

colours

1.08

Colours

1.04

XMLSchema

1.04

Activations Density 0.014%

terms related to collections and colors

No Comments

No Known Activations