INDEX

Explanations

phrases related to information confirmation or statement authentication

oai_token-act-pair · gpt-3.5-turbo

specific factual statements or announcements related to events or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

MRI

-0.76

enegger

-0.76

terness

-0.75

outube

-0.71

iliated

-0.68

VIDIA

-0.68

////////////////

-0.67

Jesus

-0.65

iets

-0.64

liv

-0.63

POSITIVE LOGITS

NP

0.61

 Span

0.60

 Proof

0.58

eki

0.58

BST

0.58

Ao

0.57

CRE

0.56

 Active

0.56

coh

0.55

 Type

0.55

Activations Density 1.743%

phrases related to information confirmation or statement authentication

specific factual statements or announcements related to events or statistics

No Comments

No Known Activations