INDEX

Explanations

locations or events associated with political rallies

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" related to events or rallies

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

omers

-0.74

CLASSIFIED

-0.74

username

-0.73

hirt

-0.70

 learners

-0.70

 engineers

-0.70

ibur

-0.70

ensor

-0.68

NOW

-0.68

¿½

-0.67

POSITIVE LOGITS

 conjunction

1.34

 lieu

1.24

 favor

1.06

 commem

1.03

 accordance

1.03

 vitro

1.03

 unison

0.99

 Charlottesville

0.95

 France

0.94

roads

0.93

Activations Density 0.432%

locations or events associated with political rallies

occurrences of the word "in" related to events or rallies

No Comments

No Known Activations