INDEX

Explanations

words starting with the letter 'z'

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'z' in close proximity within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

•words starting with z

No Comments

Negative Logits

 compe

-0.72

tenance

-0.71

Sut

-0.70

mingham

-0.69

 disadvant

-0.69

 Lumpur

-0.69

ModLoader

-0.69

 minded

-0.68

nces

-0.66

 Staples

-0.64

POSITIVE LOGITS

ebra

1.28

eros

1.17

ipped

1.14

ooming

1.09

odiac

1.06

ealous

1.05

ipping

1.03

ither

1.00

ippers

1.00

ipp

1.00

Activations Density 0.015%

words starting with the letter 'z'

instances of the letter 'z' in close proximity within the text

No Comments

No Known Activations