INDEX

Explanations

numbers associated with statistical or quantitative results

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

numerical data or statistics

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

numbers following 1

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

WithIOException

-0.78

 '\\;'

-0.76

MessageTagHelper

-0.74

 Pyrene

-0.68

 Shakspeare

-0.66

WebElementEntity

-0.64

BufferException

-0.61

 prostrate

-0.60

StoryboardSegue

-0.59

PYX

-0.59

POSITIVE LOGITS

 luật

0.54

Ad

0.50

ellant

0.45

ad

0.44

 HttpNotFound

0.43

ifah

0.43

liday

0.42

lawful

0.42

learned

0.42

 обяза

0.42

Activations Density 0.157%

numbers associated with statistical or quantitative results

numerical data or statistics

numbers following 1

No Comments

No Known Activations