INDEX

Explanations

details related to coding syntax and technical terms

oai_token-act-pair · gpt-3.5-turbo

elements related to academic grading or evaluation metrics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Authors

-0.67

 fundra

-0.59

 spotlight

-0.58

 groundwork

-0.58

 playbook

-0.57

 Rosenberg

-0.57

 library

-0.57

 sporting

-0.56

 interviewed

-0.56

 lubric

-0.56

POSITIVE LOGITS

Ħ¢

0.98

thood

0.88

anu

0.85

ãĥ©

0.83

Ïī

0.82

Ð

0.81

vantage

0.80

¹

0.78

ËĪ

0.77

_{

0.77

Activations Density 0.310%

details related to coding syntax and technical terms

elements related to academic grading or evaluation metrics

No Comments

No Known Activations