INDEX

Explanations

Unnamed characters in formatted text

oai_token-act-pair · gpt-3.5-turbo

indicators of anticipation or upcoming events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 undermin

-0.69

 neighb

-0.68

 underest

-0.67

 blinded

-0.66

 disapprove

-0.64

 biod

-0.63

 dazz

-0.61

 prosec

-0.61

 contempl

-0.61

 distances

-0.61

POSITIVE LOGITS

ÂłÂłÂłÂłÂłÂłÂłÂł

1.20

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

1.15

ÂłÂłÂłÂł

1.09

Yesterday

1.08

Thankfully

1.04

Anyway

1.01

Fortunately

1.01

ÂłÂłÂł

1.01

Naturally

0.99

Luckily

0.98

Activations Density 0.543%

Unnamed characters in formatted text

indicators of anticipation or upcoming events

No Comments

No Known Activations