INDEX

Explanations

time-related numerical data, such as percentages and specific years

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

abilities

-0.82

craft

-0.74

usb

-0.71

witch

-0.71

quit

-0.69

MK

-0.68

agy

-0.67

lia

-0.65

bending

-0.64

nel

-0.63

POSITIVE LOGITS

 latter

1.32

 same

1.24

 lowest

1.24

 heaviest

1.19

 highest

1.16

 poorest

1.15

 entire

1.10

 remainder

1.09

 average

1.09

 smallest

1.08

Activations Density 0.650%

time-related numerical data, such as percentages and specific years

occurrences of the word "the"

No Comments

No Known Activations