INDEX

Explanations

references to comparative levels of quantity or degree, particularly when something is exceeding a standard or expectation

oai_token-act-pair · gpt-3.5-turbo

quantitative phrases indicating increased spending or consumption

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

xtap

-0.93

IPS

-0.68

IDS

-0.65

 Immun

-0.64

itÃ©

-0.63

ode

-0.62

ĺħ

-0.62

align

-0.61

ovie

-0.61

SS

-0.60

POSITIVE LOGITS

 than

1.53

than

1.05

 Than

0.99

 expensive

0.93

 stringent

0.88

ado

0.85

HUD

0.84

 sophisticated

0.83

 bang

0.82

 efficient

0.81

Activations Density 0.123%

references to comparative levels of quantity or degree, particularly when something is exceeding a standard or expectation

quantitative phrases indicating increased spending or consumption

No Comments

No Known Activations