INDEX

Explanations

negations or contractions using "not."

oai_token-act-pair · gpt-3.5-turbo

negations and conditions related to uncertainty or lack of knowledge

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

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

estern

-0.94

omic

-0.68

netflix

-0.67

peat

-0.66

abal

-0.63

thood

-0.61

chet

-0.60

razil

-0.60

illet

-0.59

amic

-0.59

POSITIVE LOGITS

 thereof

0.52

aid

0.50

 subscript

0.49

 Attend

0.48

 responsibility

0.47

 inbox

0.46

 username

0.46

 periphery

0.46

 subject

0.46

eve

0.46

Activations Density 0.364%

negations or contractions using "not."

negations and conditions related to uncertainty or lack of knowledge

No Comments

No Known Activations