INDEX

Explanations

phrases indicating commitment or determination towards a specific course of action

oai_token-act-pair · gpt-3.5-turbo

phrases that refer to collective actions or sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 disadvant

-0.79

undown

-0.76

 carbohyd

-0.71

 unbeliev

-0.68

 implant

-0.66

EEG

-0.64

 misunder

-0.64

 scattering

-0.64

 offenders

-0.64

 imitation

-0.64

POSITIVE LOGITS

ï¸ı

0.98

Â·Â·

0.93

agree

0.90

å¥³

0.82

sure

0.82

mand

0.80

east

0.79

together

0.78

yg

0.78

Balt

0.77

Activations Density 0.154%

phrases indicating commitment or determination towards a specific course of action

phrases that refer to collective actions or sentiments

No Comments

No Known Activations