INDEX

Explanations

technical or scientific terms and descriptions

oai_token-act-pair · gpt-3.5-turbo

terms related to classification and labeling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

artifacts

-0.78

Lago

-0.70

atonin

-0.70

oppable

-0.70

atches

-0.69

iors

-0.67

adoes

-0.65

ents

-0.65

BLIC

-0.64

cester

-0.63

POSITIVE LOGITS

 term

2.26

 phrase

2.00

 word

2.00

 acronym

1.97

 moniker

1.87

 adjective

1.85

 terminology

1.81

 nickname

1.74

 descriptor

1.73

 abbre

1.73

Activations Density 0.435%

technical or scientific terms and descriptions

terms related to classification and labeling

No Comments

No Known Activations