INDEX

Explanations

scientific or technical terms related to categorization or classification

oai_token-act-pair · gpt-3.5-turbo

terms related to biological classification and structure

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ILLE

-0.75

hur

-0.72

Buzz

-0.70

deb

-0.68

rek

-0.67

BUS

-0.67

aughed

-0.66

Fax

-0.65

izoph

-0.65

 fumes

-0.65

POSITIVE LOGITS

 boundaries

0.99

 deline

0.95

 structure

0.95

 separating

0.94

 contiguous

0.88

 regions

0.87

separ

0.87

 dotted

0.86

 region

0.85

 comprising

0.84

Activations Density 0.547%

scientific or technical terms related to categorization or classification

terms related to biological classification and structure

No Comments

No Known Activations