INDEX

Explanations

the word "nomadic" and its variations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "nominate" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Hebdo

-0.78

 Brach

-0.69

Ble

-0.67

velt

-0.67

ween

-0.65

 prick

-0.63

ORED

-0.63

OHN

-0.63

NEY

-0.62

 dred

-0.60

POSITIVE LOGITS

inates

1.21

inally

1.17

adic

1.11

nom

1.10

atis

1.03

nom

1.02

acent

0.99

ose

0.96

inational

0.95

inators

0.95

Activations Density 0.030%

the word "nomadic" and its variations

occurrences of the term "nominate" and its variations

No Comments

No Known Activations