INDEX

Explanations

numbers

oai_token-act-pair · gpt-3.5-turbo

numeric values that may represent significant data points or measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 swearing

-0.62

 Sachs

-0.60

 Lauder

-0.59

 ment

-0.58

 Goodman

-0.58

 Cutter

-0.57

 recognition

-0.57

 Palest

-0.57

idence

-0.56

 pitched

-0.56

POSITIVE LOGITS

1.26

1.24

1.22

1.21

1.20

1.19

1.18

Activations Density 0.230%

numbers

numeric values that may represent significant data points or measures

No Comments

No Known Activations