INDEX

Explanations

proper nouns of people's names

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Don"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

âĹ¼

-0.74

PDATE

-0.73

 labour

-0.64

UID

-0.62

anwhile

-0.62

 circ

-0.60

 reluct

-0.59

ans

-0.59

 misdem

-0.58

 defic

-0.58

POSITIVE LOGITS

't

1.43

ovan

1.25

atell

1.24

nie

1.23

 Draper

1.15

nel

1.15

ner

1.11

ny

1.11

nell

1.08

ALD

1.07

Activations Density 0.031%

proper nouns of people's names

occurrences of the name "Don"

No Comments

No Known Activations