INDEX

Explanations

individuals who are new to a particular topic or community

oai_token-act-pair · gpt-3.5-turbo

phrases related to being new to a topic or community

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 likeness

-0.70

 equival

-0.65

 teasp

-0.64

verages

-0.62

 queues

-0.60

 plots

-0.59

QR

-0.59

nc

-0.58

osity

-0.58

 premiums

-0.58

POSITIVE LOGITS

entity

0.72

define

0.71

come

0.70

theless

0.70

 Emerging

0.70

here

0.69

leans

0.68

NAS

0.67

chapter

0.65

redo

0.65

Activations Density 0.140%

individuals who are new to a particular topic or community

phrases related to being new to a topic or community

No Comments

No Known Activations