INDEX

Explanations

elements related to evaluation and comparison across various scenarios or datasets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

THM

-0.49

ők

-0.48

lossians

-0.48

RenderAtEndOf

-0.47

yentes

-0.47

irited

-0.47

 Investigaciones

-0.46

 champignons

-0.46

makeText

-0.46

 zvuky

-0.45

POSITIVE LOGITS

+#+#

0.71

 lượt

0.58

 IndexPath

0.58

verwijspagina

0.58

 оба

0.57

 autorytatywna

0.57

 Beide

0.55

 виправивши

0.54

localctx

0.54

fromnode

0.54

Activations Density 1.444%

elements related to evaluation and comparison across various scenarios or datasets

No Comments

No Known Activations