INDEX

Explanations

phrases related to legal and medical terms

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the"

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

thood

-0.78

Ò

-0.77

 because

-0.68

bg

-0.68

ornings

-0.68

icia

-0.67

!!!

-0.67

xt

-0.66

verage

-0.66

POSITIVE LOGITS

 slightest

1.39

 latter

1.30

 majority

1.20

 vast

1.11

 entire

1.08

 remainder

1.08

 heaviest

1.05

 same

1.05

 biggest

1.04

 greatest

1.03

Activations Density 0.424%

phrases related to legal and medical terms

occurrences of the word "the"

No Comments

No Known Activations