INDEX

Explanations

words related to sequencing or order

oai_token-act-pair · gpt-3.5-turbo

instances of the word "followed."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

voy

-0.70

adin

-0.65

cin

-0.62

Used

-0.61

ancing

-0.61

chio

-0.59

DN

-0.58

ibr

-0.58

tons

-0.58

rait

-0.57

POSITIVE LOGITS

 closely

1.05

 suit

1.00

ĸļ

0.84

suit

0.83

 swiftly

0.74

 shortly

0.74

 thereafter

0.74

 footsteps

0.72

 logically

0.68

 immediately

0.68

Activations Density 0.035%

words related to sequencing or order

instances of the word "followed."

No Comments

No Known Activations