INDEX

Explanations

phrases related to states or conditions

oai_token-act-pair · gpt-3.5-turbo

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

 Cosponsors

-0.77

leaf

-0.71

0000000000000000

-0.70

poon

-0.64

<?

-0.64

\/\/

-0.62

poons

-0.61

orthy

-0.60

alan

-0.59

ibling

-0.59

POSITIVE LOGITS

 affairs

0.91

 Decay

0.73

URRENT

0.71

IFIED

0.68

 equilibrium

0.68

ASED

0.68

 propri

0.67

 limbo

0.67

rency

0.66

ngth

0.64

Activations Density 0.039%

phrases related to states or conditions

No Comments

No Known Activations