INDEX

Explanations

in-depth analysis or detailed examinations

oai_token-act-pair · gpt-3.5-turbo

terms related to in-depth analysis or exploration of topics

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

ade

-0.73

Alabama

-0.69

soDeliveryDate

-0.69

NOR

-0.68

Miami

-0.68

Rus

-0.68

MAR

-0.68

SY

-0.66

 Spice

-0.66

fly

-0.65

POSITIVE LOGITS

 examination

0.93

 detail

0.93

 discussions

0.90

 insight

0.86

 interviews

0.85

 disse

0.83

 insights

0.83

 penetration

0.79

 discussion

0.79

 examinations

0.77

Activations Density 0.022%

in-depth analysis or detailed examinations

terms related to in-depth analysis or exploration of topics

No Comments

No Known Activations