INDEX

Explanations

names of institutions or political entities

oai_token-act-pair · gpt-3.5-turbo

mentions of institutions or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

prem

-0.75

hai

-0.70

 Supplemental

-0.68

zos

-0.61

amaz

-0.61

ounded

-0.60

aund

-0.60

odium

-0.60

itability

-0.59

inventory

-0.59

POSITIVE LOGITS

 whatsoever

1.44

 imaginable

1.42

 conceivable

1.11

 except

1.01

 anywhere

0.89

 irrespective

0.83

soever

0.79

 thereafter

0.76

 besides

0.74

 regardless

0.71

Activations Density 0.294%

names of institutions or political entities

mentions of institutions or organizations

No Comments

No Known Activations