INDEX

Explanations

references to personal discoveries or realizations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "found" 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 @ 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

idium

-0.87

 partic

-0.71

 paced

-0.68

 attendant

-0.67

 concess

-0.64

past

-0.63

ignore

-0.63

fue

-0.60

cussion

-0.60

 aver

-0.60

POSITIVE LOGITS

ä½¿

0.80

ãĤ¤ãĥĪ

0.79

AppData

0.74

ãģ®å

0.74

unn

0.71

çīĪ

0.71

ãĤ¼

0.70

herer

0.68

usky

0.68

oliath

0.68

Activations Density 0.061%

references to personal discoveries or realizations

instances of the word "found" in various contexts

No Comments

No Known Activations