INDEX

Explanations

assumptions regarding linearity in statistical models

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

ChildScrollView

-0.59

CodeAttribute

-0.55

 DBNull

-0.55

 <=",

-0.51

 jengibre

-0.50

Rhestr

-0.48

HostException

-0.47

 calabaza

-0.47

 suéter

-0.47

 frambo

-0.47

POSITIVE LOGITS

 vettoriale

0.69

 heur

0.68

 nontrivial

0.66

 vetorial

0.66

 intuition

0.65

 conceptually

0.63

 motivates

0.63

 computationally

0.63

 motivate

0.62

 motiva

0.62

Activations Density 2.436%

assumptions regarding linearity in statistical models

No Comments

No Known Activations