INDEX

Explanations

instances of phrases starting with "According to"

oai_token-act-pair · gpt-3.5-turbo

the phrase "according to."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

anooga

-0.76

iphate

-0.72

NetMessage

-0.71

iste

-0.67

breaker

-0.65

Enlarge

-0.65

ocr

-0.64

||||

-0.64

 cared

-0.64

bodied

-0.62

POSITIVE LOGITS

 sources

1.06

 reports

1.05

 Wikipedia

1.00

reports

0.98

 legend

0.97

 insiders

0.89

 Deadline

0.85

wik

0.85

 witnesses

0.85

 eyewitness

0.84

Activations Density 0.092%

instances of phrases starting with "According to"

the phrase "according to."

No Comments

No Known Activations