INDEX

Explanations

references to locations involving the term "King."

oai_token-act-pair · gpt-3.5-turbo

references to the word "King."

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

TING

-0.78

ATIONAL

-0.76

eria

-0.75

ename

-0.74

chell

-0.71

ters

-0.71

umbai

-0.70

Availability

-0.70

uated

-0.70

ciplinary

-0.69

POSITIVE LOGITS

pin

1.21

uin

1.15

doms

1.13

dom

1.10

pins

1.09

fish

1.00

DOM

0.94

 Kong

0.91

stown

0.90

STON

0.88

Activations Density 0.024%

references to locations involving the term "King."

references to the word "King."

No Comments

No Known Activations