INDEX

Explanations

indicators of data structures and their properties

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

expandindo

-0.91

 WaitForSeconds

-0.90

ValueStyle

-0.81

SuppressLint

-0.80

nocześnie

-0.76

 CanadaChoose

-0.76

resizingMask

-0.75

InitVars

-0.72

 Wend

-0.72

NameInMap

-0.72

POSITIVE LOGITS

Dee

0.69

 Dres

0.66

mb

0.66

 обороны

0.62

 boun

0.61

 Edelman

0.60

ufficio

0.60

 Dobson

0.59

月号

0.59

 Sabrina

0.59

Activations Density 0.173%

indicators of data structures and their properties

No Comments

No Known Activations