INDEX

Explanations

terms related to myths and misconceptions

oai_token-act-pair · gpt-3.5-turbo

references to myths and misconceptions, particularly those labeled as "myth" or related terms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Interstitial

-0.77

orneys

-0.71

perature

-0.67

artney

-0.66

foreseen

-0.66

ients

-0.64

 licences

-0.63

baugh

-0.63

imentary

-0.63

affer

-0.62

POSITIVE LOGITS

icist

1.17

Myth

1.08

ril

1.01

olog

0.94

ologies

0.93

 Myth

0.91

ological

0.89

busters

0.86

ically

0.84

ic

0.82

Activations Density 0.027%

terms related to myths and misconceptions

references to myths and misconceptions, particularly those labeled as "myth" or related terms

No Comments

No Known Activations