INDEX

Explanations

people's titles and roles in various fields or organizations

oai_token-act-pair · gpt-3.5-turbo

references to roles or positions held by individuals

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

ince

-0.77

agate

-0.73

thora

-0.66

tty

-0.66

scale

-0.65

chan

-0.64

agnetic

-0.64

orce

-0.64

ESA

-0.64

chio

-0.63

POSITIVE LOGITS

 Permanent

0.76

 advoc

0.72

 honorary

0.71

 accompanying

0.69

 herself

0.69

 himself

0.67

Wid

0.66

 founding

0.66

 consequently

0.65

 alike

0.65

Activations Density 0.273%

people's titles and roles in various fields or organizations

references to roles or positions held by individuals

No Comments

No Known Activations