INDEX

Explanations

technical terms related to testing and performance evaluation

oai_token-act-pair · gpt-3.5-turbo

terms related to testing, performance, and validation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Confederation

-0.84

Ô

-0.82

itol

-0.74

acia

-0.66

 curv

-0.66

cul

-0.65

urb

-0.65

 Georgian

-0.64

 slic

-0.62

essel

-0.61

POSITIVE LOGITS

 Jury

0.64

undown

0.62

©¶æ

0.62

 sshd

0.62

 conducted

0.61

 hears

0.61

 Phelps

0.60

results

0.60

Byr

0.60

essional

0.59

Activations Density 0.893%

technical terms related to testing and performance evaluation

terms related to testing, performance, and validation processes

No Comments

No Known Activations