INDEX

Explanations

mentions of recommendations or suggestions with a positive sentiment

oai_token-act-pair · gpt-3.5-turbo

expressions indicating unfamiliarity 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ĸļ

-0.73

 Slam

-0.67

ãĥł

-0.64

emies

-0.62

NetMessage

-0.61

"}],"

-0.60

 landslide

-0.60

Els

-0.59

rog

-0.59

 landsl

-0.58

POSITIVE LOGITS

 already

0.74

fortable

0.73

 bothered

0.73

 subscrib

0.71

itus

0.69

yet

0.69

hin

0.67

epad

0.67

Know

0.66

 yourself

0.65

Activations Density 0.168%

mentions of recommendations or suggestions with a positive sentiment

expressions indicating unfamiliarity or lack of knowledge

No Comments

No Known Activations