INDEX

Explanations

references to the word "Trinity"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Trinity" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

-0.70

hard

-0.69

ARDS

-0.67

âĵĺ

-0.65

ARD

-0.65

======

-0.65

ãģ¦

-0.64

cies

-0.62

UGE

-0.62

 Archdemon

-0.62

POSITIVE LOGITS

 Trinity

1.01

inity

0.99

idad

0.76

hedral

0.75

itton

0.73

idental

0.71

pling

0.70

ync

0.70

istries

0.68

igon

0.67

Activations Density 0.004%

references to the word "Trinity"

mentions of the word "Trinity" and its variations

No Comments

No Known Activations