INDEX

Explanations

specific mentions of individuals, organizations, agreements, or actions

oai_token-act-pair · gpt-3.5-turbo

statements or claims attributed to various authorities and reports

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

ependence

-0.89

erella

-0.75

izont

-0.73

Marginal

-0.73

eways

-0.68

livion

-0.68

inge

-0.66

Merit

-0.66

oliath

-0.65

emin

-0.63

POSITIVE LOGITS

 "âĢ¦

0.94

"[

0.89

"#

0.86

"@

0.83

"'

0.78

 "...

0.76

 Paddock

0.69

:[

0.66

 spies

0.66

 fabricated

0.66

Activations Density 0.537%

specific mentions of individuals, organizations, agreements, or actions

statements or claims attributed to various authorities and reports

No Comments

No Known Activations