INDEX

Explanations

objects and their properties or attributes in a structured data format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

)|^{

-0.68

évaluateur

-0.65

miste

-0.53

<b>

-0.52

lò

-0.51

bur

-0.51

 anti

-0.49

 pacar

-0.49

old

-0.49

 Culver

-0.49

POSITIVE LOGITS

 متعلقه

0.90

tanleria

0.86

CloseOperation

0.86

Билгалдахарш

0.85

 Walkover

0.82

 ExecuteAsync

0.82

Kariera

0.81

PreExecute

0.80

⇑

0.79

 AspNetCore

0.79

Activations Density 0.103%

objects and their properties or attributes in a structured data format

No Comments

No Known Activations