INDEX

Explanations

quotations

oai_token-act-pair · gpt-3.5-turbo

instances of quoted speech

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 prec

-0.85

 prelim

-0.75

 altar

-0.75

 ranking

-0.75

pir

-0.74

 unborn

-0.74

 brid

-0.74

 rank

-0.73

 sprint

-0.71

 favor

-0.71

POSITIVE LOGITS

Really

1.22

We

1.19

Yeah

1.17

quickShipAvailable

1.17

What

1.16

Obviously

1.15

Certainly

1.15

But

1.14

Then

1.14

Because

1.14

Activations Density 0.080%

quotations

instances of quoted speech

No Comments

No Known Activations