INDEX

Explanations

possessive pronouns followed by words related to personal belongings or actions

oai_token-act-pair · gpt-3.5-turbo

possessive pronouns indicating ownership or association

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Ambro

-0.63

-0.57

 Unsure

-0.53

$$$$

-0.49

Links

-0.49

haus

-0.48

-0.47

TBD

-0.46

Jol

-0.46

POSITIVE LOGITS

own

1.09

self

0.70

 deepest

0.69

 respective

0.69

 tremend

0.68

 rightful

0.64

 newfound

0.63

 beloved

0.62

selves

0.62

 favorite

0.62

Activations Density 0.372%

possessive pronouns followed by words related to personal belongings or actions

possessive pronouns indicating ownership or association

No Comments

No Known Activations