INDEX

Explanations

instances of the term "plug-in"

oai_token-act-pair · gpt-3.5-turbo

mentions of "plug-in" related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

birth

-0.70

 Lann

-0.67

 Judgment

-0.62

swer

-0.62

########

-0.62

vict

-0.59

 prevail

-0.59

 judgement

-0.58

quez

-0.58

 Chronicle

-0.57

POSITIVE LOGITS

ging

1.51

ged

1.48

glers

1.21

gence

0.94

plug

0.92

lessly

0.90

gin

0.86

gers

0.85

gins

0.85

ges

0.81

Activations Density 0.023%

instances of the term "plug-in"

mentions of "plug-in" related concepts

No Comments

No Known Activations