INDEX

Explanations

words related to reducing or deductions

oai_token-act-pair · gpt-3.5-turbo

variations of the word "reduce."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 custody

-0.75

SAM

-0.68

 appointed

-0.65

 Shaman

-0.64

 Rahman

-0.62

 Salman

-0.62

 issued

-0.61

syn

-0.60

 categor

-0.59

steps

-0.57

POSITIVE LOGITS

uce

4.65

uces

3.53

uced

3.37

uction

2.85

ucing

2.82

ucer

2.24

uctions

2.13

uctive

1.88

uc

1.43

irect

1.18

Activations Density 0.018%

words related to reducing or deductions

variations of the word "reduce."

No Comments

No Known Activations