INDEX

Explanations

references to rankings or comparisons in datasets

oai_token-act-pair · gpt-3.5-turbo

data related to statistics and numerical information

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

pas

-0.81

pal

-0.71

krit

-0.69

 Unable

-0.69

anza

-0.68

>>>>>>>>

-0.67

Exception

-0.65

Bot

-0.64

AMY

-0.64

uala

-0.63

POSITIVE LOGITS

 respective

1.00

 different

0.90

 probabilities

0.89

 various

0.88

verages

0.85

 trends

0.85

 each

0.85

 historical

0.84

 indicators

0.84

 objectively

0.84

Activations Density 0.736%

references to rankings or comparisons in datasets

data related to statistics and numerical information

No Comments

No Known Activations