INDEX

Explanations

mentions of the organization "Coll" with varying levels of importance indicated by the activation values

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 writ

-0.71

~~~~

-0.67

fulness

-0.62

Myth

-0.61

oshenko

-0.61

isSpecialOrderable

-0.60

¥µ

-0.60

TABLE

-0.59

ItemImage

-0.58

hib

-0.58

POSITIVE LOGITS

ateral

1.43

apsed

1.30

apse

1.27

ision

1.23

ossus

1.15

oqu

1.14

iery

1.11

isions

1.10

oidal

1.08

ocation

1.05

Activations Density 0.021%

mentions of the organization "Coll" with varying levels of importance indicated by the activation values

No Comments

No Known Activations