INDEX

Explanations

instances of the word "one" followed by a number indicating a level of importance or priority

oai_token-act-pair · gpt-3.5-turbo

instances of the word "one" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ooks

-0.74

 actionGroup

-0.71

ãĥ©ãĥ³

-0.69

ories

-0.66

oof

-0.66

ãĤ¬

-0.65

Available

-0.64

emies

-0.64

inders

-0.63

ãģĤ

-0.62

POSITIVE LOGITS

 hundred

1.06

 Hundred

0.89

 thousand

0.89

 thing

0.86

 person

0.82

 sided

0.80

 glance

0.80

 wonders

0.79

esan

0.79

 embodiment

0.78

Activations Density 0.106%

instances of the word "one" followed by a number indicating a level of importance or priority

instances of the word "one" in various contexts

No Comments

No Known Activations