INDEX

Explanations

words related to personal experiences and events

oai_token-act-pair · gpt-3.5-turbo

instances of the pronoun "it" and relevant reference phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

pose

-0.69

osponsors

-0.69

 undertake

-0.65

 Flavoring

-0.63

 Capacity

-0.61

 Saying

-0.61

select

-0.61

seek

-0.59

fts

-0.59

 ILCS

-0.58

POSITIVE LOGITS

 lasted

1.64

 culminated

1.58

 resulted

1.57

 consisted

1.45

 ended

1.44

 flowed

1.42

 seemed

1.41

 amounted

1.41

 remained

1.40

 mattered

1.39

Activations Density 0.770%

words related to personal experiences and events

instances of the pronoun "it" and relevant reference phrases

No Comments

No Known Activations