INDEX

Explanations

specific entities or locations mentioned in a document

oai_token-act-pair · gpt-3.5-turbo

terms related to various institutions and organizations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Helpful

-0.92

 Verse

-0.78

 Enemies

-0.71

borgh

-0.68

DonaldTrump

-0.68

NetMessage

-0.65

Phones

-0.65

obyl

-0.64

hots

-0.64

usalem

-0.64

POSITIVE LOGITS

 operator

0.94

 administrator

0.90

 manager

0.89

 owner

0.89

 subsidiary

0.86

 directors

0.85

 operates

0.85

 employs

0.83

 employee

0.83

 operated

0.83

Activations Density 0.350%

specific entities or locations mentioned in a document

terms related to various institutions and organizations

No Comments

No Known Activations