INDEX

Explanations

references to the trading card game Magic: The Gathering

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Magic" and related concepts within a specific context

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

lishes

-0.80

romising

-0.71

 unsub

-0.70

dated

-0.68

Fas

-0.68

hovah

-0.67

fu

-0.65

heres

-0.65

nee

-0.63

lying

-0.63

POSITIVE LOGITS

 Leap

0.91

adelphia

0.81

haus

0.78

pedia

0.77

waukee

0.76

 Missile

0.75

Magic

0.74

 Beans

0.74

 Properties

0.73

ssh

0.73

Activations Density 0.017%

references to the trading card game Magic: The Gathering

mentions of the term "Magic" and related concepts within a specific context

No Comments

No Known Activations