INDEX

Explanations

adjectives expressing certainty or conclusiveness

oai_token-act-pair · gpt-3.5-turbo

words expressing certainty, ambiguity, and continuous action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 reckoning

-0.78

 straw

-0.69

 stocking

-0.66

 Masquerade

-0.63

 rooting

-0.62

Khe

-0.61

 Fritz

-0.61

 prisoner

-0.60

 Spartans

-0.60

 Sund

-0.60

POSITIVE LOGITS

ably

1.73

ently

1.65

uously

1.55

uably

1.55

ibly

1.52

ately

1.51

ously

1.50

ingly

1.44

ially

1.42

ively

1.42

Activations Density 0.102%

adjectives expressing certainty or conclusiveness

words expressing certainty, ambiguity, and continuous action

No Comments

No Known Activations