INDEX

Explanations

various references to "gap" and "hole" in the text

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

near "gap" or "hole"

np_acts-logits-general · gemini-2.0-flash

gap or hole

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

userdetails

-0.43

новништво

-0.42

oarece

-0.41

ModelAdmin

-0.40

EndInit

-0.39

UserAgent

-0.39

fjspx

-0.38

HasBeenSet

-0.38

DrawerToggle

-0.37

interopRequire

-0.36

POSITIVE LOGITS

 HOLE

0.76

Hole

0.74

hole

0.67

HOLE

0.67

 hole

0.66

 Hole

0.66

 holes

0.65

holes

0.63

 Holes

0.62

Holes

0.59

Activations Density 0.264%

various references to "gap" and "hole" in the text

near "gap" or "hole"

gap or hole

No Comments

No Known Activations