INDEX

Explanations

references to a specific location or person named "Adi"

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals or entities, particularly with the suffix '-adi'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

TON

-0.79

tle

-0.77

ãĥ¼ãĥ«

-0.76

size

-0.75

take

-0.74

lier

-0.74

theless

-0.74

ertodd

-0.74

fully

-0.73

glers

-0.73

POSITIVE LOGITS

Äĩ

1.22

emi

0.95

ennes

0.91

plom

0.90

ya

0.88

ye

0.81

arbon

0.79

qa

0.76

oun

0.75

ETH

0.74

Activations Density 0.031%

references to a specific location or person named "Adi"

mentions of specific individuals or entities, particularly with the suffix '-adi'

No Comments

No Known Activations