INDEX

Explanations

phrases containing the word "row"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "row" and variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

merce

-0.86

ãĥ¤

-0.80

omorphic

-0.75

urated

-0.72

 mathemat

-0.71

urate

-0.70

ural

-0.68

achev

-0.68

 superficial

-0.68

 competence

-0.68

POSITIVE LOGITS

dy

1.41

dies

1.25

boat

0.85

row

0.84

dale

0.83

Room

0.82

bean

0.82

angles

0.82

nd

0.80

ser

0.80

Activations Density 0.011%

phrases containing the word "row"

instances of the word "row" and variations of it

No Comments

No Known Activations