INDEX

Explanations

mentions of the word "hash" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

complexContent

-0.71

">//

-0.64

+#+#

-0.59

 XCTest

-0.58

MessageState

-0.57

processable

-0.57

prepareStatement

-0.56

parsedMessage

-0.55

Personensuche

-0.55

tvguidetime

-0.55

POSITIVE LOGITS

ash

0.65

harusnya

0.64

 Ashford

0.60

ASH

0.60

ash

0.55

VARIANT

0.53

 olvidar

0.53

Barcelona

0.53

mstyle

0.53

visiae

0.52

Activations Density 0.124%

mentions of the word "hash" in various contexts

No Comments

No Known Activations