INDEX

Explanations

occurrences of social media posts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "posted."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

inho

-0.73

idge

-0.71

isma

-0.71

icably

-0.68

ppo

-0.66

hart

-0.65

 Galile

-0.64

phant

-0.64

pter

-0.64

 Gand

-0.63

POSITIVE LOGITS

 posting

0.91

posted

0.91

uploads

0.90

 postings

0.86

gres

0.83

 posts

0.82

ulate

0.81

doctoral

0.81

hum

0.78

 posted

0.77

Activations Density 0.025%

occurrences of social media posts

instances of the word "posted."

No Comments

No Known Activations