INDEX

Explanations

phrases related to question and answer (Q&A) sessions

oai_token-act-pair · gpt-3.5-turbo

references to Q&A formats or sessions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ufact

-0.83

 phased

-0.70

SPONSORED

-0.69

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.69

 Hutchinson

-0.67

 Plum

-0.64

icent

-0.63

 inev

-0.62

ãĤ¼ãĤ¦ãĤ¹

-0.62

readable

-0.61

POSITIVE LOGITS

FAQ

0.84

qs

0.73

aq

0.69

 Emails

0.67

º

0.64

 selections

0.64

Timer

0.63

 Interview

0.63

 unanswered

0.63

Ds

0.63

Activations Density 0.037%

phrases related to question and answer (Q&A) sessions

references to Q&A formats or sessions

No Comments

No Known Activations