INDEX

Explanations

descriptions of actions or events happening

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to getting information or sneak peeks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

orrow

-0.76

 withdrawing

-0.69

 coerc

-0.67

 inval

-0.66

 Delete

-0.65

 unemploy

-0.65

 delet

-0.64

 constitu

-0.63

 bankrupt

-0.63

 debts

-0.63

POSITIVE LOGITS

 glimpse

1.77

 glimps

1.70

 peek

1.45

 firsthand

1.35

 insight

1.25

 insider

1.06

 taste

1.05

 sneak

1.04

 preview

1.01

 insights

1.00

Activations Density 0.365%

descriptions of actions or events happening

words and phrases related to getting information or sneak peeks

No Comments

No Known Activations