INDEX

Explanations

uses of certain objects or substances in various contexts

oai_token-act-pair · gpt-3.5-turbo

the term "use" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Barg

-0.72

Vie

-0.67

Zur

-0.63

 Huck

-0.63

 Beir

-0.62

 Sandwich

-0.61

Wem

-0.59

 passage

-0.59

 Barron

-0.59

bitious

-0.58

POSITIVE LOGITS

fulness

1.22

fully

1.11

FUL

1.09

ful

0.99

full

0.96

ability

0.88

ible

0.82

lessness

0.78

ables

0.78

ibility

0.76

Activations Density 0.049%

uses of certain objects or substances in various contexts

the term "use" in various contexts

No Comments

No Known Activations