INDEX

Explanations

verbs related to significant actions taken by individuals or organizations

oai_token-act-pair · gpt-3.5-turbo

actions related to legal, political, or contentious events

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

 âĶľâĶĢâĶĢ

-0.72

ivable

-0.69

respective

-0.65

iner

-0.63

ahime

-0.61

inen

-0.60

 âĶľ

-0.60

dds

-0.59

 ILCS

-0.59

ccording

-0.58

POSITIVE LOGITS

 theirs

0.90

 hers

0.76

 unexpectedly

0.74

 unsuccessfully

0.71

him

0.70

 them

0.67

 prematurely

0.64

 Schwe

0.64

 mysteriously

0.63

 abruptly

0.62

Activations Density 0.433%

verbs related to significant actions taken by individuals or organizations

actions related to legal, political, or contentious events

No Comments

No Known Activations