INDEX

Explanations

technical terms related to evaluation, assessment, and review

oai_token-act-pair · gpt-3.5-turbo

terms related to testing and evaluation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

bold

-0.66

 Vict

-0.66

 Citation

-0.61

blue

-0.61

Church

-0.56

Registered

-0.55

 Authors

-0.54

 Cele

-0.54

 sender

-0.54

 juicy

-0.54

POSITIVE LOGITS

 conducted

1.03

spection

0.96

 undertaken

0.89

 ensued

0.86

tests

0.83

cation

0.82

 process

0.81

 performed

0.76

 culminating

0.76

 procedure

0.75

Activations Density 0.338%

technical terms related to evaluation, assessment, and review

terms related to testing and evaluation processes

No Comments

No Known Activations