INDEX

Explanations

questions ending in a question mark

oai_token-act-pair · gpt-3.5-turbo

questions related to the consequences or implications of various topics

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

agos

-0.78

 carbohyd

-0.78

 transition

-0.73

 slightest

-0.72

rael

-0.71

 exting

-0.70

rontal

-0.68

 fused

-0.67

 bonded

-0.67

oki

-0.67

POSITIVE LOGITS

 Well

1.77

 Firstly

1.41

Well

1.37

 Probably

1.34

 Quite

1.33

 Apparently

1.33

 Surely

1.32

 Plenty

1.32

 Answer

1.30

 Certainly

1.28

Activations Density 0.082%

questions ending in a question mark

questions related to the consequences or implications of various topics

No Comments

No Known Activations