INDEX

Explanations

expressions related to losing or misplacing something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "lost" and related concepts of loss or disorientation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

IPS

-0.71

IOR

-0.70

independent

-0.63

ucci

-0.63

Independent

-0.62

 Monitor

-0.61

Ir

-0.60

oran

-0.60

Fax

-0.60

APH

-0.60

POSITIVE LOGITS

 virginity

1.00

 tiss

0.86

 dignity

0.79

 grasp

0.79

 pursu

0.76

 traction

0.76

owship

0.74

ãĤª

0.73

 glory

0.71

 composure

0.71

Activations Density 0.173%

expressions related to losing or misplacing something

instances of the word "lost" and related concepts of loss or disorientation

No Comments

No Known Activations