INDEX

Explanations

terms related to data structures and programming concepts

oai_token-act-pair · gpt-3.5-turbo

references to structural elements or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ously

-0.70

hood

-0.69

 Yellowstone

-0.68

cale

-0.67

 Clarkson

-0.67

mph

-0.64

 Leone

-0.64

 Sierra

-0.63

 Hitman

-0.63

frey

-0.63

POSITIVE LOGITS

urally

1.49

ured

1.27

ural

1.15

atile

1.08

uring

1.06

uration

1.04

rait

1.03

urer

0.99

ures

0.99

untarily

0.94

Activations Density 0.010%

terms related to data structures and programming concepts

references to structural elements or concepts

No Comments

No Known Activations