INDEX

Explanations

occurrences of the word 'lapse'

oai_token-act-pair · gpt-3.5-turbo

instances of the word "laps" and related terms, indicating a focus on interruptions or breaks in continuity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bush

-0.66

 Square

-0.63

ISON

-0.62

 CARE

-0.61

 Occupy

-0.61

 AMERICA

-0.60

 Trop

-0.60

GROUP

-0.60

Square

-0.58

NH

-0.57

POSITIVE LOGITS

 laps

1.23

es

0.89

imil

0.85

lap

0.83

luster

0.82

atile

0.81

manship

0.80

crew

0.79

alos

0.77

len

0.76

Activations Density 0.004%

occurrences of the word 'lapse'

instances of the word "laps" and related terms, indicating a focus on interruptions or breaks in continuity

No Comments

No Known Activations