INDEX

Explanations

keywords related to television channels

oai_token-act-pair · gpt-3.5-turbo

references to television networks or programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

-0.75

hot

-0.73

cule

-0.67

ãĤ¬

-0.66

 otherwise

-0.64

htaking

-0.64

 Pelosi

-0.61

 lazy

-0.61

 Lennon

-0.61

 sequ

-0.60

POSITIVE LOGITS

ILLE

1.11

iolet

0.94

TV

0.90

NG

0.88

BO

0.82

NZ

0.81

 Everywhere

0.81

atcher

0.80

OM

0.79

ideos

0.78

Activations Density 0.010%

keywords related to television channels

references to television networks or programs

No Comments

No Known Activations