INDEX

Explanations

items or services mentioned within a text

oai_token-act-pair · gpt-3.5-turbo

references to items in a list or inventory

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

orks

-0.84

sburgh

-0.71

 Doodle

-0.67

 Winds

-0.65

ILLE

-0.64

Gib

-0.64

BILITY

-0.64

doms

-0.61

 Telegram

-0.61

 Dunk

-0.60

POSITIVE LOGITS

meal

0.93

ized

0.92

izer

0.90

ious

0.88

urgical

0.87

izers

0.86

ization

0.85

istics

0.85

iser

0.84

aclysm

0.83

Activations Density 0.026%

items or services mentioned within a text

references to items in a list or inventory

No Comments

No Known Activations