INDEX

Explanations

phrases that refer to explanations or definitions in simple and explicit language

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

in terms of

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 AssemblyCulture

-0.73

 مرئيه

-0.60

 Normdatei

-0.60

 wireType

-0.55

DoubleQuotes

-0.54

Архівовано

-0.52

Chham

-0.51

 createState

-0.50

 consultato

-0.49

protoimpl

-0.48

POSITIVE LOGITS

 terms

0.55

 words

0.42

 términos

0.41

 termes

0.41

terms

0.41

 Worten

0.35

Words

0.35

 termos

0.35

 Stornier

0.34

Terms

0.33

Activations Density 0.052%

phrases that refer to explanations or definitions in simple and explicit language

in terms of

No Comments

No Known Activations