INDEX

Explanations

references to specific statistical methods and theories in causal inference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 nakalista

-1.15

 postId

-0.90

LogFactory

-0.86

ymce

-0.83

 }^{(

-0.82

 Garry

-0.82

 recensement

-0.81

SLR

-0.80

 onFailure

-0.80

PRD

-0.80

POSITIVE LOGITS

Pin

0.71

Tar

0.70

Gil

0.68

ạch

0.67

 broche

0.65

kab

0.65

íslu

0.64

Gil

0.63

opatra

0.63

pin

0.61

Activations Density 2.818%

references to specific statistical methods and theories in causal inference

No Comments

No Known Activations