INDEX

Explanations

phrases using the word "One" to refer to a specific item or moment

oai_token-act-pair · gpt-3.5-turbo

patterns of repetition or enumeration in descriptions of events or memories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

osponsors

-0.70

adobe

-0.70

byss

-0.65

="#

-0.64

icultural

-0.63

apons

-0.63

 enshr

-0.62

AMD

-0.62

contained

-0.62

ailable

-0.62

POSITIVE LOGITS

 thing

1.23

 nights

1.22

guy

1.19

 evenings

1.02

 mornings

1.01

 summers

1.00

 weekends

0.99

day

0.95

 days

0.95

 dude

0.92

Activations Density 0.403%

phrases using the word "One" to refer to a specific item or moment

patterns of repetition or enumeration in descriptions of events or memories

No Comments

No Known Activations