INDEX

Explanations

references to different types of wines

oai_token-act-pair · gpt-3.5-turbo

mentions of wine

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

aneous

-0.81

aneously

-0.79

ulation

-0.72

ordinate

-0.72

ulu

-0.70

urat

-0.70

uled

-0.70

DonaldTrump

-0.69

urtle

-0.68

 WATCHED

-0.68

POSITIVE LOGITS

 wine

1.16

 tasting

1.12

wine

1.09

 vinegar

1.08

 grapes

1.05

 cellar

1.00

 tast

0.96

 wines

0.93

 vine

0.92

 Wine

0.88

Activations Density 0.011%

references to different types of wines

mentions of wine

No Comments

No Known Activations