INDEX

Explanations

phrases related to actions or activities that the individual has been doing

oai_token-act-pair · gpt-3.5-turbo

the phrase "I have been" in various contexts

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

lies

-0.72

izable

-0.69

rones

-0.68

terday

-0.68

Must

-0.67

ives

-0.66

iop

-0.66

regate

-0.65

Guy

-0.64

idental

-0.64

POSITIVE LOGITS

 subjected

1.03

 able

1.03

 unable

1.03

 tasked

0.95

 accused

0.93

 forgiven

0.91

 criticized

0.91

 warned

0.89

 punished

0.89

 rewarded

0.89

Activations Density 0.126%

phrases related to actions or activities that the individual has been doing

the phrase "I have been" in various contexts

No Comments

No Known Activations