INDEX

Explanations

proper names being with the word "Gene"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Gene."

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

yrim

-0.82

 Pradesh

-0.82

etheless

-0.81

izoph

-0.80

Demand

-0.78

ecause

-0.78

footed

-0.77

ulhu

-0.77

committee

-0.75

uckland

-0.72

POSITIVE LOGITS

alogy

1.16

alog

1.01

Gene

0.91

llo

0.90

 Simmons

0.90

 Smith

0.87

ber

0.78

cci

0.77

Kru

0.75

elsen

0.75

Activations Density 0.010%

proper names being with the word "Gene"

occurrences of the name "Gene."

No Comments

No Known Activations