INDEX

Explanations

specific entities or categories related to notable individuals and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

énario

-0.57

 automatiques

-0.54

 EClass

-0.53

SPATH

-0.50

odeon

-0.49

 emot

-0.48

rophes

-0.46

jména

-0.45

cheer

-0.45

 peccato

-0.44

POSITIVE LOGITS

scalatest

0.79

 مشين

0.59

verwijspagina

0.59

RegistryLite

0.58

prnewswire

0.58

DebuggerStep

0.57

AutoScale

0.56

MessageTagHelper

0.54

 kasarigan

0.54

 springfox

0.54

Activations Density 0.387%

specific entities or categories related to notable individuals and events

No Comments

No Known Activations