INDEX

Explanations

phrases indicating numerical values or time references

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

numbers

np_acts-logits-general · gemini-2.0-flash

text

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

SequentialGroup

-0.43

一句

-0.40

 HFILL

-0.39

 line

-0.38

 Line

-0.36

 headline

-0.35

 LINE

-0.31

つける

-0.29

这句话

-0.29

Line

-0.29

POSITIVE LOGITS

 text

1.05

 texte

1.04

 textes

0.94

 texts

0.94

 texto

0.89

 Texte

0.85

 textos

0.84

 текста

0.84

 tekst

0.80

text

0.80

Activations Density 0.343%

phrases indicating numerical values or time references

numbers

text

No Comments

No Known Activations