INDEX

Explanations

First person singular pronouns followed by verbs in the present tense

oai_token-act-pair · gpt-3.5-turbo

instances of the first-person pronoun "I" and variations related to personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Constitutional

-0.76

WWF

-0.65

 Rugby

-0.65

 Cameroon

-0.60

 Failure

-0.60

 Permanent

-0.58

population

-0.58

 Gender

-0.58

 Newspaper

-0.58

 Bolshevik

-0.58

POSITIVE LOGITS

'll

1.01

uler

0.96

pher

0.96

 shouldn

0.93

 could

0.88

ctic

0.87

athered

0.87

 wouldn

0.86

're

0.86

å£

0.86

Activations Density 0.116%

First person singular pronouns followed by verbs in the present tense

instances of the first-person pronoun "I" and variations related to personal experiences

No Comments

No Known Activations