INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Buck."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 agre

-0.70

 Sloan

-0.65

($)

-0.57

ournal

-0.54

casts

-0.53

 Kham

-0.53

 seiz

-0.53

 Worlds

-0.53

Correct

-0.53

 forbidden

-0.53

POSITIVE LOGITS

abee

1.18

ety

1.08

ett

1.05

aroo

1.01

whe

1.00

etts

1.00

horn

0.99

lesh

0.99

ets

0.98

alo

0.97

Activations Density 0.079%

proper nouns

occurrences of the name "Buck."

No Comments

No Known Activations