INDEX

Explanations

JSON syntax patterns within the text

oai_token-act-pair · gpt-3.5-turbo

elements and structures related to error messages or data formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Jericho

-0.72

 unmarked

-0.68

 convict

-0.66

 impunity

-0.66

ĺħ

-0.66

itives

-0.65

 abduct

-0.65

 voic

-0.64

 unsolved

-0.62

 whist

-0.62

POSITIVE LOGITS

":{"

1.03

ItemImage

0.98

isSpecialOrderable

0.88

":["

0.87

quickShipAvailable

0.86

tnc

0.85

":[{"

0.85

price

0.82

ãĥĺãĥ©

0.81

isu

0.80

Activations Density 0.016%

JSON syntax patterns within the text

elements and structures related to error messages or data formatting

No Comments

No Known Activations