INDEX

Explanations

examples or instances of various concepts or phenomena

oai_token-act-pair · gpt-3.5-turbo

instances of the word "examples" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

yssey

-0.68

 Fury

-0.68

iasis

-0.68

 Indigo

-0.67

mosp

-0.65

inal

-0.64

light

-0.64

 unification

-0.64

roller

-0.63

 monop

-0.63

POSITIVE LOGITS

 examples

0.99

 thereof

0.90

amples

0.86

 illustrating

0.83

icles

0.82

DragonMagazine

0.79

baugh

0.75

 depicting

0.73

uations

0.73

etting

0.70

Activations Density 0.028%

examples or instances of various concepts or phenomena

instances of the word "examples" and its variations

No Comments

No Known Activations