INDEX

Explanations

phrases related to uncertainty or questions

oai_token-act-pair · gpt-3.5-turbo

textual elements related to legal proceedings or courtroom dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 centrally

-0.81

etheless

-0.76

 estranged

-0.72

vit

-0.67

 altru

-0.65

 este

-0.65

stad

-0.64

 colleg

-0.64

 camoufl

-0.64

 territ

-0.63

POSITIVE LOGITS

Pause

1.00

Shock

0.92

Reply

0.88

Narr

0.87

DAQ

0.86

Said

0.83

Movie

0.83

Episode

0.82

IRC

0.80

Response

0.80

Activations Density 0.158%

phrases related to uncertainty or questions

textual elements related to legal proceedings or courtroom dialogue

No Comments

No Known Activations