INDEX

Explanations

words related to social media behavior, such as "posted" and "selfie"

oai_token-act-pair · gpt-3.5-turbo

instances of posts or sharing content on social media platforms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

itect

-0.70

clave

-0.66

osi

-0.65

ichick

-0.63

ahime

-0.61

cale

-0.60

 Lauder

-0.59

umbledore

-0.59

YD

-0.59

essen

-0.59

POSITIVE LOGITS

 pics

1.12

 screenshots

1.10

 pictures

1.02

 photos

1.01

Tweet

0.98

 onto

0.94

 selfies

0.94

 flyers

0.90

 tweets

0.89

 selfie

0.89

Activations Density 0.234%

words related to social media behavior, such as "posted" and "selfie"

instances of posts or sharing content on social media platforms

No Comments

No Known Activations