INDEX

Explanations

numerical figures, particularly ones related to items for sale

oai_token-act-pair · gpt-3.5-turbo

numerical identifiers or rankings, likely related to specific entities or categories

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

gerald

-0.80

manship

-0.63

 "$:/

-0.60

enegger

-0.58

ural

-0.56

rolet

-0.56

Ik

-0.56

utan

-0.55

 sway

-0.55

ured

-0.54

POSITIVE LOGITS

nd

2.09

ND

1.19

1.09

1.07

0.98

 externalToEVAOnly

0.94

 thirds

0.94

0.93

Activations Density 0.123%

numerical figures, particularly ones related to items for sale

numerical identifiers or rankings, likely related to specific entities or categories

No Comments

No Known Activations