INDEX

Explanations

instances of the word "Morgan" followed by a numeric value

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Morgan."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

lihood

-0.91

ract

-0.75

ľ

-0.72

ensions

-0.68

ension

-0.68

uously

-0.66

================================================================

-0.65

 Carbuncle

-0.64

 vested

-0.64

èª

-0.62

POSITIVE LOGITS

igans

0.87

dale

0.86

 Chase

0.84

gage

0.80

ican

0.79

wagen

0.77

 Stanley

0.76

imet

0.75

riages

0.75

 Burnett

0.75

Activations Density 0.007%

instances of the word "Morgan" followed by a numeric value

mentions of the name "Morgan."

No Comments

No Known Activations