INDEX

Explanations

mentions of arrays

oai_token-act-pair · gpt-3.5-turbo

instances of the word "array" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ife

-0.74

quit

-0.71

ief

-0.70

Joh

-0.69

 Mens

-0.66

win

-0.65

Roy

-0.65

 Cooper

-0.65

 Kard

-0.64

 Chill

-0.63

POSITIVE LOGITS

 array

3.69

 arrays

2.52

 Array

2.31

array

2.27

Array

1.85

 assortment

1.53

 arsenal

1.15

 range

1.14

 constellation

1.04

 multitude

1.04

Activations Density 0.020%

mentions of arrays

instances of the word "array" and its variations

No Comments

No Known Activations