INDEX

Explanations

specific instances of logic and causation in complex arguments

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

InitVars

-0.65

 Bess

-0.65

MessageState

-0.64

}}">

-0.62

Приятного

-0.59

 réglable

-0.59

 Monfieur

-0.58

 Theſe

-0.57

 Leiden

-0.57

 Jefus

-0.57

POSITIVE LOGITS

 שוליים

0.63

@[+][

0.56

 дописавши

0.53

errHandler

0.51

ագրություններ

0.50

 تضيفلها

0.48

TProtocol

0.48

隈

0.47

WireFormatLite

0.46

cro

0.46

Activations Density 1.224%

specific instances of logic and causation in complex arguments

No Comments

No Known Activations