INDEX

Explanations

proper nouns related to the name "Morrison"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Mor" across various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Reboot

-0.75

pta

-0.73

 Tycoon

-0.73

 sockets

-0.66

BOOK

-0.66

JECT

-0.62

âĸ¬

-0.62

ctive

-0.61

ãĥ¼ãĥĨãĤ£

-0.61

 Carbuncle

-0.59

POSITIVE LOGITS

pheus

1.30

imoto

1.04

rigan

1.01

atorium

0.98

rison

0.90

als

0.87

neau

0.86

iculture

0.85

aff

0.84

icultural

0.83

Activations Density 0.020%

proper nouns related to the name "Morrison"

mentions of the name "Mor" across various contexts

No Comments

No Known Activations