INDEX

Explanations

infinitive verb phrases indicating purpose or intention

oai_token-act-pair · gpt-3.5-turbo

the usage of the word "to" 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

UDP

-0.68

 newsp

-0.65

esson

-0.64

typ

-0.63

 shortages

-0.61

 masks

-0.60

 expecting

-0.57

 Apart

-0.57

groupon

-0.55

 excluding

-0.54

POSITIVE LOGITS

be

0.92

 take

0.89

iling

0.85

 fulfill

0.83

 prove

0.83

kes

0.82

 emulate

0.82

 participate

0.81

 help

0.80

 overtake

0.79

Activations Density 0.113%

infinitive verb phrases indicating purpose or intention

the usage of the word "to" in various contexts

No Comments

No Known Activations