INDEX

Explanations

comparisons of quantities or likelihoods

oai_token-act-pair · gpt-3.5-turbo

comparative phrases related to likelihood and efficiency

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

Mand

-0.90

elle

-0.67

dra

-0.66

DC

-0.66

DES

-0.63

RAW

-0.62

dec

-0.62

Eye

-0.62

Chart

-0.62

selection

-0.62

POSITIVE LOGITS

 than

1.03

than

0.88

 Than

0.83

olesterol

0.72

acters

0.71

bilt

0.71

enegger

0.69

per

0.67

itsu

0.65

illion

0.64

Activations Density 0.091%

comparisons of quantities or likelihoods

comparative phrases related to likelihood and efficiency

No Comments

No Known Activations