INDEX

Explanations

numerical data and comparisons

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

the number seven

np_acts-logits-general · gemini-2.0-flash

seven and seven

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Borne

-0.53

verwijspagina

-0.53

nial

-0.53

onus

-0.52

<![

-0.52

arna

-0.51

haden

-0.50

 Archae

-0.50

 associate

-0.49

 Anastasia

-0.49

POSITIVE LOGITS

1.53

 seventh

1.29

 seven

1.29

 Seven

1.26

 Seventh

1.21

 SEVEN

1.15

seven

1.13

Seventh

1.11

七

1.10

Seven

1.09

Activations Density 0.759%

numerical data and comparisons

the number seven

seven and seven

No Comments

No Known Activations