INDEX

Explanations

phrases indicating putting an end or taking action on something

oai_token-act-pair · gpt-3.5-turbo

articles preceding nouns

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

assisted

-0.70

!/

-0.69

 endeavors

-0.63

 preferring

-0.61

 incorpor

-0.60

peak

-0.60

lins

-0.59

mins

-0.58

 pursuits

-0.58

Easy

-0.58

POSITIVE LOGITS

lot

1.21

 bunch

1.12

 handful

0.98

 huge

0.89

few

0.89

 sizable

0.87

 sizeable

0.85

 bead

0.84

 piece

0.83

 couple

0.82

Activations Density 0.211%

phrases indicating putting an end or taking action on something

articles preceding nouns

No Comments

No Known Activations