INDEX

Explanations

phrases related to WWE and wrestling events

oai_token-act-pair · gpt-3.5-turbo

references to WWE and its events, specifically focusing on its wrestlers and championships

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

heid

-0.86

anwhile

-0.85

ouver

-0.83

 MacArthur

-0.80

emort

-0.79

 BART

-0.77

elong

-0.77

lasses

-0.76

uries

-0.75

perse

-0.73

POSITIVE LOGITS

restling

1.10

NXT

1.07

Mania

1.01

 Universe

0.98

 Wrestle

0.90

 wrestlers

0.81

 Championship

0.81

WWE

0.80

 Wrest

0.79

 wrestling

0.78

Activations Density 0.024%

phrases related to WWE and wrestling events

references to WWE and its events, specifically focusing on its wrestlers and championships

No Comments

No Known Activations