INDEX

Explanations

technical terms related to data analytics and performance evaluation

oai_token-act-pair · gpt-3.5-turbo

topics related to performance metrics and evaluation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hement

-0.81

tsky

-0.80

terday

-0.80

etta

-0.76

 destro

-0.71

elin

-0.69

etheless

-0.66

ueller

-0.65

efe

-0.65

hene

-0.65

POSITIVE LOGITS

Marginal

0.90

ccording

0.89

========

0.83

 Prices

0.80

 Removal

0.80

============

0.79

Language

0.75

":["

0.74

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.74

Disclaimer

0.72

Activations Density 0.179%

technical terms related to data analytics and performance evaluation

topics related to performance metrics and evaluation

No Comments

No Known Activations