INDEX

Explanations

quotations within a text

oai_token-act-pair · gpt-3.5-turbo

instances of direct quotations or speech in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 scheduled

-0.83

 cannabin

-0.82

 adjud

-0.81

 favor

-0.77

 schedule

-0.73

 graded

-0.72

 resettlement

-0.71

 surfaced

-0.71

 midterm

-0.70

 distingu

-0.70

POSITIVE LOGITS

We

1.15

1.10

Our

1.05

Hey

1.02

heter

1.00

Dear

0.99

Everyone

0.99

Absolutely

0.97

Walk

0.96

It

0.96

Activations Density 0.081%

quotations within a text

instances of direct quotations or speech in the text

No Comments

No Known Activations