INDEX

Explanations

locations or positions within a visual interface

oai_token-act-pair · gpt-3.5-turbo

terms related to screens, documents, or visual displays

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

 sqor

-0.72

awi

-0.66

ãĥīãĥ©

-0.64

theless

-0.64

ãģķ

-0.64

 Cosponsors

-0.63

ãĥŃ

-0.62

 fals

-0.61

 stockp

-0.60

ãĥ¥

-0.58

POSITIVE LOGITS

enium

0.83

isphere

0.81

 hierarchy

0.79

 rectangle

0.73

ifice

0.71

advertising

0.70

ieu

0.70

osphere

0.70

 continuum

0.69

 hemisphere

0.69

Activations Density 0.493%

locations or positions within a visual interface

terms related to screens, documents, or visual displays

No Comments

No Known Activations