INDEX

Explanations

phrases indicating continuation or monitoring of actions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating ongoing actions or commitments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ById

-0.75

 forgot

-0.71

OME

-0.70

Suddenly

-0.70

licted

-0.69

ãĤ¨ãĥ«

-0.68

irez

-0.67

ellar

-0.67

 slips

-0.66

Could

-0.66

POSITIVE LOGITS

 vigorously

1.17

 strive

1.16

 vigil

1.00

 aggressively

1.00

 endeav

0.99

 vigilance

0.98

 vigilant

0.98

 endeavour

0.98

 cooperate

0.93

 efforts

0.89

Activations Density 0.196%

phrases indicating continuation or monitoring of actions

phrases indicating ongoing actions or commitments

No Comments

No Known Activations