INDEX

Explanations

loose ends or loose items

oai_token-act-pair · gpt-3.5-turbo

variations of the word "loose" and related concepts of untidiness or incompleteness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

++++

-0.72

oleon

-0.71

urga

-0.68

issance

-0.68

ococ

-0.68

reon

-0.68

ior

-0.68

orea

-0.67

aurus

-0.65

ophobia

-0.64

POSITIVE LOGITS

leaf

1.14

 coupling

0.95

 cannon

0.94

 ends

0.90

 morals

0.90

 Ends

0.85

cloth

0.84

 leaf

0.80

nesses

0.77

fitting

0.77

Activations Density 0.026%

loose ends or loose items

variations of the word "loose" and related concepts of untidiness or incompleteness

No Comments

No Known Activations