INDEX

Explanations

negative statements or implications

oai_token-act-pair · gpt-3.5-turbo

negative qualifiers and expressions of doubt or uncertainty

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

Negative Logits

kamp

-0.69

plex

-0.68

lance

-0.67

ceiver

-0.62

place

-0.61

Shares

-0.61

file

-0.60

 Line

-0.59

imeters

-0.59

charges

-0.59

POSITIVE LOGITS

 outright

0.94

 necessarily

0.84

eworthy

0.81

acular

0.78

ifies

0.75

 entirely

0.72

icably

0.71

 exactly

0.68

withstanding

0.68

 technically

0.68

Activations Density 0.026%

negative statements or implications

negative qualifiers and expressions of doubt or uncertainty

No Known Activations