INDEX

Explanations

phrases related to titles, names, and legal documents

oai_token-act-pair · gpt-3.5-turbo

phrases that reference origin or relationship

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

aments

-0.67

 respectively

-0.64

 isEnabled

-0.62

iscopal

-0.62

 chem

-0.60

åĳ

-0.60

finder

-0.59

aft

-0.58

raised

-0.57

 leaflets

-0.57

POSITIVE LOGITS

itialized

0.94

slaught

0.80

 Them

0.74

tes

0.71

Us

0.71

 Month

0.70

ymm

0.69

 Taken

0.67

semb

0.67

Him

0.67

Activations Density 0.147%

phrases related to titles, names, and legal documents

phrases that reference origin or relationship

No Comments

No Known Activations