INDEX

Explanations

mentions or references of Instagram accounts

oai_token-act-pair · gpt-3.5-turbo

mentions of the social media platform Instagram

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

neg

-0.68

endez

-0.64

CFR

-0.62

 lesser

-0.62

 Constitutional

-0.60

 Ambrose

-0.59

 Oaks

-0.59

 Jefferson

-0.58

Nep

-0.58

 Winds

-0.57

POSITIVE LOGITS

 Instagram

0.97

mable

0.93

photos

0.91

mers

0.85

Lens

0.82

ster

0.76

mentation

0.75

 feeds

0.74

 pics

0.74

agram

0.73

Activations Density 0.008%

mentions or references of Instagram accounts

mentions of the social media platform Instagram

No Comments

No Known Activations