INDEX

Explanations

names of specific entities such as places, organizations, and individuals within a political context

oai_token-act-pair · gpt-3.5-turbo

mentions of specific people, organizations, or geopolitical entities

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

DEN

-0.68

Skip

-0.58

 Fukushima

-0.58

Loading

-0.58

 Tasman

-0.57

Enlarge

-0.56

 northwestern

-0.56

COMPLE

-0.56

Hidden

-0.55

xon

-0.55

POSITIVE LOGITS

selves

0.89

 cares

0.88

ain

0.83

 sucks

0.77

 hates

0.76

 loves

0.76

 existed

0.71

 motto

0.69

 greatness

0.67

 enthus

0.67

Activations Density 0.531%

names of specific entities such as places, organizations, and individuals within a political context

mentions of specific people, organizations, or geopolitical entities

No Comments

No Known Activations

names of specific entities such as places, organizations, and individuals within a political context

mentions of specific people, organizations, or geopolitical entities

No Comments

No Known Activations