INDEX

Explanations

mentions of specific durations of time, particularly those related to sentences or imprisonments

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" followed by various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

NOW

-0.78

hirt

-0.71

ALSE

-0.68

mu

-0.67

pointers

-0.65

bryce

-0.65

tons

-0.64

DOS

-0.64

SourceFile

-0.63

deck

-0.63

POSITIVE LOGITS

 advance

1.08

ordinate

1.00

 accordance

1.00

 preparation

0.96

 lieu

0.94

 conjunction

0.93

 vitro

0.93

 relation

0.91

 order

0.91

patient

0.91

Activations Density 0.255%

mentions of specific durations of time, particularly those related to sentences or imprisonments

occurrences of the word "in" followed by various contexts

No Comments

No Known Activations