INDEX

Explanations

mentions of legal terms or specificity in text

oai_token-act-pair · gpt-3.5-turbo

occurrences of the prefix "Pl" in words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

âĸ¬âĸ¬

-0.81

âĸ¬

-0.77

 Siri

-0.66

~~~~

-0.66

 FANTASY

-0.63

NEY

-0.63

 CONTROL

-0.62

 constitu

-0.61

worthiness

-0.61

SPONSORED

-0.60

POSITIVE LOGITS

atinum

1.50

asma

1.46

enty

1.41

ausible

1.39

utonium

1.36

acement

1.36

umbing

1.28

acements

1.21

atoon

1.20

anned

1.20

Activations Density 0.018%

mentions of legal terms or specificity in text

occurrences of the prefix "Pl" in words

No Comments

No Known Activations