INDEX

Explanations

references to the word "Young"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Young" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

++++++++++++++++

-0.83

DCS

-0.79

ossession

-0.78

acle

-0.76

igslist

-0.75

oute

-0.72

ãĥ¤

-0.71

arium

-0.70

illin

-0.70

adr

-0.70

POSITIVE LOGITS

blood

1.17

lings

1.14

stown

0.98

sters

0.98

ster

0.94

ness

0.91

sta

0.90

zin

0.88

moon

0.85

Tang

0.83

Activations Density 0.021%

references to the word "Young"

occurrences of the name "Young" in various contexts

No Comments

No Known Activations