INDEX

Explanations

instances where a word is emphasized or highlighted in a text

oai_token-act-pair · gpt-3.5-turbo

quotes or phrases that convey strong opinions or sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Ļ½

-0.84

İĭ

-0.81

Ń·

-0.80

bris

-0.68

tein

-0.67

ĻĤ

-0.66

isl

-0.66

nas

-0.66

²¾

-0.65

»Ĵ

-0.65

POSITIVE LOGITS

Journal

0.68

 translates

0.68

 Greenpeace

0.67

/"

0.66

 reads

0.65

++

0.65

 refers

0.65

 GOODMAN

0.61

 Blog

0.60

 trailed

0.58

Activations Density 0.146%

instances where a word is emphasized or highlighted in a text

quotes or phrases that convey strong opinions or sentiments

No Comments

No Known Activations