INDEX

Explanations

exclamatory phrases indicating personal insights or observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ImageContext

-0.54

principalTable

-0.53

apnews

-0.53

 fallu

-0.52

 насељу

-0.49

rrggbb

-0.48

AppMethodBeat

-0.47

rección

-0.47

shadowOffset

-0.46

 consultato

-0.46

POSITIVE LOGITS

 disponibilités

0.62

CodedInputStream

0.61

خصة

0.60

 gather

0.57

urten

0.57

 Bioaccumulative

0.57

XmlEnum

0.56

 infer

0.56

WireFormatLite

0.56

TProtocol

0.55

Activations Density 0.139%

exclamatory phrases indicating personal insights or observations

No Comments

No Known Activations