INDEX

Explanations

settings or locations where events take place

oai_token-act-pair · gpt-3.5-turbo

instances of the word "set" associated with various contexts in films or narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

issance

-0.83

ishable

-0.71

ibly

-0.69

vernment

-0.67

ãĤĭ

-0.67

IBLE

-0.63

aud

-0.63

ãĥīãĥ©ãĤ´ãĥ³

-0.63

asive

-0.62

Cola

-0.60

POSITIVE LOGITS

offs

1.01

tle

0.94

list

0.89

piece

0.87

ters

0.85

opsis

0.84

lists

0.83

TING

0.80

rac

0.79

itia

0.78

Activations Density 0.042%

settings or locations where events take place

instances of the word "set" associated with various contexts in films or narratives

No Comments

No Known Activations