INDEX

Explanations

mentions of the word "Gran" in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Gran" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Laugh

-0.67

 Lovecraft

-0.64

 Gutenberg

-0.62

 favorable

-0.60

{"

-0.60

 stocks

-0.59

 practiced

-0.59

 fright

-0.59

 Schumer

-0.59

hered

-0.58

POSITIVE LOGITS

ularity

1.28

ular

1.18

itic

0.98

itary

0.98

vier

0.92

itas

0.90

izo

0.87

etti

0.86

ulate

0.86

ules

0.85

Activations Density 0.016%

mentions of the word "Gran" in various contexts

mentions of the word "Gran" in various contexts

No Comments

No Known Activations