INDEX

Explanations

mentions of the name "Rick" in varying contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Rick."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ournal

-0.86

bom

-0.70

rul

-0.66

*/(

-0.65

ulhu

-0.61

 elig

-0.60

vict

-0.60

00200000

-0.59

 incent

-0.59

SAR

-0.59

POSITIVE LOGITS

 Santorum

1.17

etts

1.16

 Grimes

1.07

 Berman

1.00

ety

0.98

 Rick

0.96

Rick

0.90

ards

0.87

leness

0.86

iness

0.86

Activations Density 0.019%

mentions of the name "Rick" in varying contexts

mentions of the name "Rick."

No Comments

No Known Activations