INDEX

Explanations

instances of the word "Can" with various capitalizations and prefixes

oai_token-act-pair · gpt-3.5-turbo

references to "CAN" and its variations, particularly in the context of product names or branding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

edient

-0.71

VERTISEMENT

-0.70

edded

-0.68

eering

-0.67

furt

-0.64

 honoring

-0.62

æī

-0.61

 ORDER

-0.61

 rehearsal

-0.60

 striving

-0.60

POSITIVE LOGITS

vas

1.28

adian

1.22

't

1.19

berra

1.14

opy

1.00

atell

0.97

nery

0.89

tera

0.89

iac

0.86

NOT

0.85

Activations Density 0.031%

instances of the word "Can" with various capitalizations and prefixes

references to "CAN" and its variations, particularly in the context of product names or branding

No Comments

No Known Activations