INDEX

Explanations

words related to technology and equipment, particularly those with specific types or models

oai_token-act-pair · gpt-3.5-turbo

terms and phrases associated with medical or health-related classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Rodrigo

-0.72

vel

-0.68

Wyn

-0.67

 McKay

-0.67

DERR

-0.66

 Zucker

-0.65

 Wake

-0.64

 Targ

-0.63

 Tuls

-0.63

Ri

-0.63

POSITIVE LOGITS

appropriate

0.95

conscious

0.94

specific

0.92

changing

0.90

Specific

0.89

wise

0.86

gallery

0.86

checking

0.86

relation

0.85

definition

0.84

Activations Density 0.126%

words related to technology and equipment, particularly those with specific types or models

terms and phrases associated with medical or health-related classifications

No Comments

No Known Activations