INDEX

Explanations

names or words with the letter 'j' with a strong activation value

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "j"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Not in Any Lists

No Comments

Negative Logits

 Lauder

-0.72

 dispers

-0.71

 rooting

-0.71

 prolific

-0.68

 Scotia

-0.66

milo

-0.66

 Contra

-0.66

 outgoing

-0.65

CONCLUS

-0.64

 arming

-0.64

POSITIVE LOGITS

ournals

1.42

itsu

1.29

ordan

1.24

acket

1.19

unction

1.15

utsu

1.13

ealous

1.09

ij

1.08

unal

1.07

oking

1.05

Activations Density 0.021%

names or words with the letter 'j' with a strong activation value

occurrences of the letter "j"

No Comments

No Known Activations