INDEX

Explanations

sequences of numbers and characters that might relate to technical information or data leaks

oai_token-act-pair · gpt-3.5-turbo

numeric identifiers or codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 millenn

-0.75

DonaldTrump

-0.70

 whiff

-0.65

 stret

-0.65

 globalization

-0.64

 strongest

-0.61

 mutual

-0.60

 slightest

-0.59

 brightest

-0.58

worldly

-0.58

POSITIVE LOGITS

ae

0.93

wr

0.86

0.85

fe

0.83

0.81

}:

0.80

ea

0.79

0.78

ac

0.77

Activations Density 0.014%

sequences of numbers and characters that might relate to technical information or data leaks

numeric identifiers or codes

No Comments

No Known Activations