INDEX

Explanations

quotes spoken by someone

oai_token-act-pair · gpt-3.5-turbo

dialogue or quotes attributed to speakers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 mosqu

-0.67

ardless

-0.66

ogether

-0.66

senal

-0.62

 unprotected

-0.62

ortunately

-0.61

 conflic

-0.60

 destro

-0.58

 veter

-0.57

levant

-0.57

POSITIVE LOGITS

 said

0.64

 Nasa

0.63

 Peck

0.62

 chuck

0.59

 Elsa

0.58

 Klopp

0.57

 Osborne

0.57

Sgt

0.57

 Blasio

0.57

 Singh

0.56

Activations Density 0.303%

quotes spoken by someone

dialogue or quotes attributed to speakers

No Comments

No Known Activations