INDEX

Explanations

personal pronouns followed by verbs

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "you."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Reconstruction

-0.67

 Dimension

-0.64

 Lives

-0.62

 Jasper

-0.62

course

-0.62

 Actions

-0.61

 Sunset

-0.60

 Pulitzer

-0.60

 Hours

-0.60

 Integrity

-0.59

POSITIVE LOGITS

're

1.40

've

1.14

 hear

1.09

 realize

0.97

 realise

0.95

 guys

0.94

 think

0.90

hei

0.89

 contemplate

0.88

 compare

0.86

Activations Density 0.095%

personal pronouns followed by verbs

occurrences of the word "you."

No Comments

No Known Activations