INDEX

Explanations

statistical references and indicators of findings in research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 المعيارى

-0.85

AndEndTag

-0.75

CloseOperation

-0.73

verwijspagina

-0.72

évaluateur

-0.72

 according

-0.70

stdc

-0.69

 nahilalakip

-0.69

 ComVisible

-0.67

دانشنامهٔ

-0.65

POSITIVE LOGITS

 bahwa

0.56

 bahawa

0.55

 that

0.52

によると

0.51

 indicate

0.49

 menyebut

0.47

 mourir

0.47

BagLayout

0.45

 أنه

0.45

 réserver

0.45

Activations Density 0.459%

statistical references and indicators of findings in research contexts

No Comments

No Known Activations