INDEX

Explanations

mentions of the name "Michael Konecan"

oai_token-act-pair · gpt-3.5-turbo

the verb "can" 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

VERTISEMENT

-0.81

edient

-0.81

pires

-0.67

 classy

-0.66

 cheated

-0.63

 rehearsal

-0.63

æī

-0.61

 Cortex

-0.60

che

-0.59

 wonderful

-0.59

POSITIVE LOGITS

adian

1.26

berra

1.21

't

1.19

vas

1.16

tera

0.96

nery

0.91

opy

0.87

thus

0.87

throp

0.86

icum

0.85

Activations Density 0.004%

mentions of the name "Michael Konecan"

the verb "can" in various contexts

No Comments

No Known Activations