INDEX

Explanations

phrases related to receiving information or feedback

oai_token-act-pair · gpt-3.5-turbo

instances of feedback or complaints received

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

clud

-0.73

heid

-0.69

raint

-0.65

 cure

-0.62

 econom

-0.62

lou

-0.61

 Cure

-0.59

ocracy

-0.59

 muscles

-0.59

 segreg

-0.58

POSITIVE LOGITS

 requests

1.53

 inquiries

1.45

 complaints

1.40

 queries

1.27

 emails

1.24

 calls

1.14

 petitions

1.13

mails

1.12

 request

1.09

 enqu

1.08

Activations Density 0.344%

phrases related to receiving information or feedback

instances of feedback or complaints received

No Comments

No Known Activations