INDEX

Explanations

phrases related to being referred to as or known as something specific

oai_token-act-pair · gpt-3.5-turbo

terms related to software installation and references to entities or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

azaki

-0.71

eor

-0.68

orthy

-0.65

erest

-0.63

icult

-0.63

 dissu

-0.63

 appeals

-0.60

 unsett

-0.60

ashington

-0.60

animate

-0.60

POSITIVE LOGITS

çīĪ

0.88

 ç¥ŀ

0.86

 abbrevi

0.84

"#

0.80

 acron

0.77

ãĥ³ãĤ¸

0.76

 Fancy

0.75

MJ

0.75

ËĪ

0.75

``

0.73

Activations Density 0.270%

phrases related to being referred to as or known as something specific

terms related to software installation and references to entities or titles

No Comments

No Known Activations