INDEX

Explanations

words related to changes or transformations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'b'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Plex

-0.74

bilt

-0.73

 Pharaoh

-0.67

 Gutenberg

-0.67

 Nadu

-0.66

 Deity

-0.66

OPLE

-0.64

ãĤ¦ãĤ¹

-0.64

 Spartan

-0.64

tenance

-0.63

POSITIVE LOGITS

rows

1.18

ibli

1.16

abb

1.14

idd

1.12

ibliography

1.07

raid

1.05

rawn

1.04

uch

1.03

abbling

1.03

aked

1.02

Activations Density 0.022%

words related to changes or transformations

occurrences of the letter 'b'

No Comments

No Known Activations