INDEX

Explanations

recognition awards and accolades for individuals in various fields

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

etsk

-0.71

 preparations

-0.66

aird

-0.65

 tunnels

-0.64

 scanning

-0.63

 analys

-0.63

eria

-0.63

adan

-0.62

 centrif

-0.62

 surrog

-0.62

POSITIVE LOGITS

 Excellence

0.80

 Month

0.80

 Americas

0.77

ãĥĦ

0.72

 Week

0.68

 Choice

0.68

 Award

0.68

 Chains

0.68

 Rocks

0.67

Hon

0.67

Activations Density 0.101%

recognition awards and accolades for individuals in various fields

No Comments

No Known Activations