INDEX

Explanations

connections between different locations or entities within a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.67

 󰀄

-0.59

JIT

-0.50

 Prolog

-0.48

DAW

-0.47

υναι

-0.47

 DeFi

-0.45

 Capcom

-0.45

 Duterte

-0.45

 Slovenian

-0.45

POSITIVE LOGITS

ThroughAttribute

0.73

 calendriers

0.68

tencent

0.67

NACIONAL

0.66

자인

0.65

La

0.64

InsertCommand

0.64

spesies

0.63

fycat

0.62

addCriterion

0.62

Activations Density 1.140%

connections between different locations or entities within a narrative context

No Comments

No Known Activations