INDEX

Explanations

scientific terms and data related to research methodologies and findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 виправивши

-0.96

 للمعارف

-0.71

+#+#

-0.68

TypedDataSet

-0.68

ValueStyle

-0.66

 '\\;'

-0.62

parsedMessage

-0.62

featureID

-0.61

CodedInputStream

-0.61

IntoConstraints

-0.60

POSITIVE LOGITS

 hundreds

2.32

 dozens

2.21

 thousands

2.12

hundreds

1.98

 Hundreds

1.84

thousands

1.80

Hundreds

1.78

 nine

1.75

 eight

1.75

 ratusan

1.74

Activations Density 1.052%

scientific terms and data related to research methodologies and findings

No Comments

No Known Activations