INDEX

Explanations

phrases indicating the passage of time

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the passage of time

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

MIS

-0.61

chest

-0.61

 Nass

-0.60

Atlantic

-0.59

 Collector

-0.58

Mog

-0.57

boa

-0.56

gencies

-0.56

ippi

-0.55

Tar

-0.55

POSITIVE LOGITS

adays

1.13

abouts

0.98

here

0.97

iatus

0.81

tics

0.76

heres

0.74

lease

0.73

 devoted

0.72

 compr

0.72

 defunct

0.68

Activations Density 0.040%

phrases indicating the passage of time

phrases indicating the passage of time

No Comments

No Known Activations