INDEX

Explanations

sentences that end with a full stop

oai_token-act-pair · gpt-3.5-turbo

sentences expressing positive evaluations or reviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

idal

-0.80

 contingency

-0.80

 involuntary

-0.78

 renegoti

-0.77

 casualty

-0.77

 inference

-0.76

 determin

-0.76

 disadvantage

-0.74

 concess

-0.73

uer

-0.72

POSITIVE LOGITS

 Firstly

1.54

 Especially

1.51

 Located

1.37

 Lots

1.34

 Particularly

1.32

 Featuring

1.29

 Including

1.29

 Seriously

1.27

 Literally

1.26

 Having

1.25

Activations Density 0.385%

sentences that end with a full stop

sentences expressing positive evaluations or reviews

No Comments

No Known Activations