INDEX

Explanations

place names and historical events

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

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 @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

Bet

-0.70

 Rebels

-0.67

 Ground

-0.66

 young

-0.64

 teasing

-0.64

due

-0.62

 Monarch

-0.61

 âĢķ

-0.61

 Crimson

-0.60

 midway

-0.59

POSITIVE LOGITS

osph

1.28

ishops

1.22

oreal

1.19

ibi

1.18

ajor

1.16

ibli

1.15

ilib

1.14

ikini

1.11

aku

1.09

AFTA

1.09

Activations Density 0.029%

place names and historical events

occurrences of the letter 'B'

No Comments

No Known Activations