INDEX

Explanations

references to a specific movie or TV show titled "Legend."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "legend" 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 @ 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

abus

-0.76

earcher

-0.70

 Parenthood

-0.67

pex

-0.66

artment

-0.65

 Goods

-0.65

 concession

-0.64

lyak

-0.60

 agitation

-0.60

orneys

-0.60

POSITIVE LOGITS

arily

1.30

arium

0.91

naire

0.88

aries

0.88

Legend

0.83

lore

0.80

arious

0.79

 Incarn

0.76

 Reborn

0.76

ous

0.75

Activations Density 0.023%

references to a specific movie or TV show titled "Legend."

occurrences of the word "legend" in various contexts

No Comments

No Known Activations