INDEX

Explanations

words related to the name "Brand" or variations of it

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Brand" and related references throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 attendant

-0.78

 compensated

-0.63

Tsu

-0.60

ancial

-0.60

 STAT

-0.59

DAY

-0.58

pmwiki

-0.58

 circadian

-0.58

 derailed

-0.58

 Fukushima

-0.58

POSITIVE LOGITS

enburg

1.40

olph

1.05

olini

1.03

enstein

1.02

enberg

0.95

0.89

olf

0.88

stown

0.87

reth

0.86

oris

0.86

Activations Density 0.045%

words related to the name "Brand" or variations of it

occurrences of the name "Brand" and related references throughout the text

No Comments

No Known Activations