INDEX

Explanations

instances of the word "when"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "when."

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

agin

-0.76

gan

-0.72

rolet

-0.71

zzi

-0.70

yan

-0.65

gem

-0.65

hole

-0.64

idan

-0.64

ictive

-0.64

aking

-0.63

POSITIVE LOGITS

soever

1.39

 confronted

0.82

irlf

0.81

 faced

0.80

 contrasted

0.76

 compared

0.76

 comparing

0.74

ŃĶ

0.68

©¶æ

0.68

 pressed

0.67

Activations Density 0.122%

instances of the word "when"

instances of the word "when."

No Comments

No Known Activations