INDEX

Explanations

names of various people

oai_token-act-pair · gpt-3.5-turbo

proper names, particularly those related to individuals and 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Perception

-0.76

 Italians

-0.61

 Ryder

-0.61

 Brav

-0.60

 Slovenia

-0.58

unity

-0.57

 Wolves

-0.56

 Citiz

-0.56

 demoral

-0.56

 Colossus

-0.56

POSITIVE LOGITS

Jr

0.97

nr

0.93

vard

0.82

Sr

0.82

aka

0.82

ensen

0.81

III

0.74

iman

0.74

itars

0.74

velt

0.71

Activations Density 0.335%

names of various people

proper names, particularly those related to individuals and organizations

No Comments

No Known Activations