INDEX

Explanations

interviews and mentions of specific names, such as interviewees and interviewers

oai_token-act-pair · gpt-3.5-turbo

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

acci

-0.85

 ILCS

-0.75

 sexes

-0.68

holes

-0.67

 separ

-0.65

ain

-0.65

angular

-0.65

 barg

-0.65

 leveling

-0.64

 except

-0.64

POSITIVE LOGITS

 CNBC

1.21

CNN

1.21

 reporters

1.19

NBC

1.15

ABC

1.15

 MSNBC

1.13

 interviewer

1.12

ITV

1.11

 Vanity

1.11

BBC

1.10

Activations Density 0.116%

interviews and mentions of specific names, such as interviewees and interviewers

No Comments

No Known Activations