INDEX

Explanations

the presence of significant or impactful punctuation and formatting cues in the text

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

non-English or specialized terms

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 this

-0.58

 Summary

-0.54

 этого

-0.48

 summarise

-0.47

 dieses

-0.47

นี้

-0.47

 SUMMARY

-0.47

 generated

-0.46

Summary

-0.46

 summary

-0.46

POSITIVE LOGITS

you

0.66

 your

0.53

 zrozum

0.48

HomeAsUpEnabled

0.46

 semblent

0.46

 Италијани

0.45

 você

0.45

AndEndTag

0.44

uride

0.44

帖最后由

0.44

Activations Density 0.000%

the presence of significant or impactful punctuation and formatting cues in the text

non-English or specialized terms

No Comments

No Known Activations