INDEX

Explanations

phrases containing the word "Trans"

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

RANT

-0.86

 Sunder

-0.75

 maker

-0.68

ARD

-0.66

FUL

-0.65

mble

-0.65

eer

-0.65

 footing

-0.63

ously

-0.63

 prick

-0.62

POSITIVE LOGITS

cend

1.19

mission

1.11

lator

1.09

gender

1.08

latable

1.05

parency

1.05

missions

1.04

mitt

1.04

itional

1.03

istors

1.03

Activations Density 0.014%

phrases containing the word "Trans"

No Comments

No Known Activations