INDEX

Explanations

phrases containing the word "me."

oai_token-act-pair · gpt-3.5-turbo

the pronoun "me."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rama

-0.79

ulation

-0.79

hips

-0.72

olor

-0.70

roads

-0.70

road

-0.68

umar

-0.67

esses

-0.65

ultz

-0.65

rieved

-0.65

POSITIVE LOGITS

asure

1.13

anwhile

1.12

lda

0.99

ister

0.94

zzo

0.91

adow

0.90

gang

0.90

leon

0.90

adows

0.89

asured

0.87

Activations Density 0.025%

phrases containing the word "me."

the pronoun "me."

No Comments

No Known Activations