INDEX

Explanations

Italian words

oai_token-act-pair · gpt-3.5-turbo

terms related to digital information and analysis

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Bench

-0.63

Moore

-0.62

made

-0.60

luck

-0.60

short

-0.59

rified

-0.57

USD

-0.57

TP

-0.57

Tokens

-0.57

Sadly

-0.56

POSITIVE LOGITS

Ã±

1.00

ÃŁ

0.93

Ã«

0.90

ennes

0.90

endas

0.89

Ã°

0.89

Äĩ

0.88

endum

0.87

Å¡

0.85

Ã±o

0.84

Activations Density 0.105%

Italian words

terms related to digital information and analysis

No Known Activations