INDEX

Explanations

sports-related terms, specifically related to the Toronto Maple Leafs hockey team

oai_token-act-pair · gpt-3.5-turbo

references to sports teams and athletes

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

 destro

-0.59

 respectively

-0.56

SPONSORED

-0.55

Interstitial

-0.55

 thereof

-0.55

$$$$

-0.54

 âĢ¦"

-0.53

 thereto

-0.52

jri

-0.52

 Kardash

-0.50

POSITIVE LOGITS

 Profile

0.72

xiety

0.50

 Edit

0.49

Wiki

0.48

omon

0.46

clair

0.46

::

0.46

utsu

0.44

":{"

0.44

 Texture

0.44

Activations Density 0.611%

sports-related terms, specifically related to the Toronto Maple Leafs hockey team

references to sports teams and athletes

No Comments

No Known Activations