INDEX

Explanations

mentions of geographic locations

oai_token-act-pair · gpt-3.5-turbo

references to the "state of" followed by various subjects or topics

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

 Cosponsors

-0.71

ï¸ı

-0.64

 Harbor

-0.61

<?

-0.59

Claim

-0.58

ishable

-0.58

ier

-0.58

0000000000000000

-0.57

 Donation

-0.57

aron

-0.57

POSITIVE LOGITS

 Decay

0.85

 affairs

0.82

rency

0.68

ngth

0.66

vironment

0.64

foundland

0.62

ortunately

0.62

 equilibrium

0.62

IFIED

0.62

braska

0.61

Activations Density 0.051%

mentions of geographic locations

references to the "state of" followed by various subjects or topics

No Comments

No Known Activations