INDEX

Explanations

occurrences of the token "omm" at various activations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "omm" within words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ted

-0.88

ting

-0.86

BOOK

-0.75

footed

-0.70

JUST

-0.70

 Hindus

-0.67

TRUMP

-0.66

Charges

-0.65

realDonaldTrump

-0.64

FORE

-0.62

POSITIVE LOGITS

obile

1.17

ittee

1.17

orrow

1.15

essage

1.14

ission

0.98

ando

0.98

acent

0.97

orr

0.95

useum

0.95

ajor

0.93

Activations Density 0.007%

occurrences of the token "omm" at various activations

occurrences of the substring "omm" within words

No Comments

No Known Activations