INDEX

Explanations

pronouns 'we' and 'our'

oai_token-act-pair · gpt-3.5-turbo

references to collective responsibility or shared experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

REDACTED

-0.77

 Publication

-0.66

 gratification

-0.64

odor

-0.64

 Crush

-0.61

cum

-0.60

Owner

-0.60

personal

-0.59

 Hole

-0.58

 Levine

-0.58

POSITIVE LOGITS

're

1.22

've

1.21

'll

0.99

athered

0.98

akening

0.98

asel

0.96

 ourselves

0.95

ird

0.93

lder

0.92

IRD

0.92

Activations Density 0.239%

pronouns 'we' and 'our'

references to collective responsibility or shared experiences

No Comments

No Known Activations