INDEX

Explanations

Twitter usernames

oai_token-act-pair · gpt-3.5-turbo

social media handles or usernames

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

 margins

-0.83

 ACTIONS

-0.75

 jaws

-0.74

 solvent

-0.74

 soil

-0.71

 warranties

-0.66

 tense

-0.66

 embodiments

-0.64

 technicians

-0.63

 overfl

-0.63

POSITIVE LOGITS

Jew

0.96

_.

0.95

Jr

0.93

PB

0.87

Twe

0.87

_(

0.86

Buff

0.83

York

0.82

ibrary

0.80

Activations Density 0.147%

Twitter usernames

social media handles or usernames

No Comments

No Known Activations