INDEX

Explanations

technical specifications such as sizes, measurements, and capacities

oai_token-act-pair · gpt-3.5-turbo

technical specifications and measurements

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

know

-0.78

eering

-0.67

Fear

-0.67

developed

-0.66

ivist

-0.65

laws

-0.64

etta

-0.62

asia

-0.62

conscious

-0.61

Bir

-0.60

POSITIVE LOGITS

 increments

1.28

 apiece

1.15

/$

1.10

+)

1.04

+.

1.03

avg

1.02

+,

1.01

0.98

 maximum

0.87

Avg

0.87

Activations Density 0.105%

technical specifications such as sizes, measurements, and capacities

technical specifications and measurements

No Comments

No Known Activations