INDEX

Explanations

phrases related to negative outcomes or consequences

oai_token-act-pair · gpt-3.5-turbo

statements and questions that imply situations or challenges faced by individuals

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

tera

-0.88

vertisement

-0.76

 phased

-0.66

aeus

-0.66

itled

-0.62

 shaved

-0.61

igree

-0.61

 bounded

-0.61

ijing

-0.59

 uptake

-0.59

POSITIVE LOGITS

 Lastly

1.99

 Finally

1.83

Lastly

1.53

Finally

1.52

etc

1.45

 These

1.30

etc

1.26

These

1.25

 Whatever

1.25

 Needless

1.22

Activations Density 0.622%

phrases related to negative outcomes or consequences

statements and questions that imply situations or challenges faced by individuals

No Comments

No Known Activations