INDEX

Explanations

occurrences of specific terms related to .NET technology

oai_token-act-pair · gpt-3.5-turbo

mentions of "NET" as it relates to technology and applications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Synopsis

-0.71

ively

-0.69

aca

-0.67

isters

-0.67

quez

-0.67

 Fukushima

-0.66

ende

-0.65

 Enrique

-0.64

 Aval

-0.62

Bj

-0.60

POSITIVE LOGITS

WORK

1.31

hester

0.92

heastern

0.91

anyahu

0.90

NET

0.85

working

0.83

FL

0.82

runner

0.82

heast

0.80

shaw

0.79

Activations Density 0.010%

occurrences of specific terms related to .NET technology

mentions of "NET" as it relates to technology and applications

No Comments

No Known Activations