INDEX

Explanations

words related to the utilization or application of resources or tools

oai_token-act-pair · gpt-3.5-turbo

instances of the word "use" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Bom

-0.70

 Barron

-0.67

 Bert

-0.65

 Barg

-0.65

 Mous

-0.64

olulu

-0.63

 Griff

-0.62

 Gord

-0.61

 Tale

-0.61

 notch

-0.61

POSITIVE LOGITS

fulness

1.09

fully

1.08

FUL

0.93

ability

0.87

ful

0.86

full

0.84

rences

0.80

nels

0.79

ivation

0.76

iences

0.76

Activations Density 0.056%

words related to the utilization or application of resources or tools

instances of the word "use" in various contexts

No Comments

No Known Activations