INDEX

Explanations

the word "em" followed by various suffixes like "bers", "blazoned", "ulators", "bezzlement" and "ce" among others

oai_token-act-pair · gpt-3.5-turbo

the prefix "em" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

aird

-0.73

 Lovecraft

-0.73

RAW

-0.72

 Draw

-0.71

 Hitch

-0.70

DragonMagazine

-0.69

 Idle

-0.68

 Kavanaugh

-0.67

 Kubrick

-0.66

 Wynne

-0.65

POSITIVE LOGITS

igrants

1.32

igrant

1.25

igration

1.17

igrated

1.15

blems

1.13

bers

1.09

perors

1.08

igr

1.06

acs

1.05

otions

1.03

Activations Density 0.012%

the word "em" followed by various suffixes like "bers", "blazoned", "ulators", "bezzlement" and "ce" among others

the prefix "em" in various contexts

No Comments

No Known Activations