INDEX

Explanations

mentions of the politician Marco Rubio

oai_token-act-pair · gpt-3.5-turbo

mentions of Marco Rubio

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 à¨

-0.91

à¨

-0.79

ļ

-0.70

lehem

-0.69

apolis

-0.67

arers

-0.66

Ö¼

-0.65

ulhu

-0.64

elf

-0.64

 antioxid

-0.64

POSITIVE LOGITS

 Rubio

1.08

xtap

0.83

Cruz

0.79

bite

0.76

 Cruz

0.74

cair

0.72

 Caucus

0.69

 fielded

0.68

bian

0.68

uth

0.67

Activations Density 0.007%

mentions of the politician Marco Rubio

mentions of Marco Rubio

No Comments

No Known Activations