INDEX

Explanations

adverbs describing the frequency of an action

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "regularly" and its synonyms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ANG

-0.61

 Verse

-0.61

 Illusion

-0.58

states

-0.57

 misunderstanding

-0.57

isSpecialOrderable

-0.57

oldemort

-0.55

 guess

-0.55

 Translation

-0.55

 confusion

-0.55

POSITIVE LOGITS

 regularly

3.31

 routinely

2.49

 frequently

2.32

 periodically

2.24

 constantly

1.91

 consistently

1.84

 occasionally

1.81

 continually

1.78

 frequent

1.69

 continuously

1.63

Activations Density 0.014%

adverbs describing the frequency of an action

occurrences of the word "regularly" and its synonyms

No Comments

No Known Activations