INDEX

Explanations

names of locations, specifically related to a certain state

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Rakhine" in various contexts

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

 Polo

-0.93

ĸļ

-0.83

 Collider

-0.76

PLIED

-0.71

 McCartney

-0.63

PRESS

-0.60

atories

-0.59

OPLE

-0.59

erva

-0.58

 Griff

-0.58

POSITIVE LOGITS

urst

1.08

amaz

1.07

iak

0.90

assium

0.88

amia

0.85

rites

0.84

oslov

0.82

ritis

0.81

achev

0.81

ansas

0.81

Activations Density 0.029%

names of locations, specifically related to a certain state

mentions of the term "Rakhine" in various contexts

No Comments

No Known Activations