INDEX

Explanations

words related to legal cases and proceedings

oai_token-act-pair · gpt-3.5-turbo

references to "ins" which may relate to institutions or organizations

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

 compr

-0.67

 Prime

-0.63

¥µ

-0.62

hovah

-0.62

llan

-0.62

 Achieve

-0.62

 Bulgar

-0.62

bral

-0.62

lling

-0.62

aeper

-0.61

POSITIVE LOGITS

pection

1.29

urance

1.14

piration

1.10

ufficient

1.08

anity

1.03

pect

1.02

piring

1.01

poon

0.95

uit

0.93

ergic

0.92

Activations Density 0.034%

words related to legal cases and proceedings

references to "ins" which may relate to institutions or organizations

No Comments

No Known Activations