INDEX

Explanations

mentions or references to licensing or legal terms

oai_token-act-pair · gpt-3.5-turbo

words related to licensing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Unch

-0.74

thing

-0.74

 Lans

-0.69

 Everywhere

-0.65

skirts

-0.64

ahime

-0.63

ħĭ

-0.63

commit

-0.62

 Ended

-0.61

 Rabbit

-0.61

POSITIVE LOGITS

ensing

1.37

hess

1.14

enses

1.12

entious

0.95

ensable

0.94

atable

0.93

ious

0.92

henko

0.90

enced

0.87

hester

0.87

Activations Density 0.021%

mentions or references to licensing or legal terms

words related to licensing

No Comments

No Known Activations