INDEX

Explanations

the name "Silva" with different variations and contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Silva"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

rians

-0.75

ERAL

-0.71

rium

-0.70

neys

-0.70

printed

-0.70

giving

-0.66

rian

-0.66

bear

-0.66

selves

-0.66

LEASE

-0.65

POSITIVE LOGITS

 Silva

1.06

iola

0.81

 Paulo

0.81

 Alvarez

0.79

imar

0.69

 mosqu

0.68

 Gonzalez

0.68

uth

0.67

 Ramos

0.67

da

0.67

Activations Density 0.007%

the name "Silva" with different variations and contexts

mentions of the name "Silva"

No Comments

No Known Activations