INDEX

Explanations

references to the television series "My Little Pony"

oai_token-act-pair · gpt-3.5-turbo

titles and names associated with specific media franchises

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

irez

-0.79

warts

-0.76

orescence

-0.74

 popul

-0.73

aff

-0.73

ooming

-0.72

ily

-0.70

rum

-0.68

rils

-0.67

ensor

-0.67

POSITIVE LOGITS

 Bastard

1.06

 Sexy

1.06

 Baseball

1.03

 Lonely

1.03

 Dancing

1.01

 Deadly

1.00

 Stupid

1.00

 Murder

0.98

 Adventure

0.98

 Mahjong

0.98

Activations Density 0.204%

references to the television series "My Little Pony"

titles and names associated with specific media franchises

No Comments

No Known Activations