INDEX

Explanations

companies or organizations

oai_token-act-pair · gpt-3.5-turbo

company and brand names

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

asta

-0.69

-0.67

chest

-0.65

rn

-0.64

uminati

-0.64

berra

-0.64

>>>>

-0.63

isode

-0.63

alys

-0.60

 Brett

-0.59

POSITIVE LOGITS

 spokesperson

0.70

 Ventures

0.69

 spokesman

0.69

's

0.67

 executives

0.66

 experimented

0.66

 shareholders

0.66

 officials

0.65

 Customer

0.65

 Transparency

0.63

Activations Density 0.368%

companies or organizations

company and brand names

No Comments

No Known Activations