INDEX

Explanations

names of individuals and their titles or roles

oai_token-act-pair · gpt-3.5-turbo

coordinating conjunctions, particularly "and."

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

CRIP

-0.81

BUR

-0.74

iotics

-0.73

plings

-0.73

Ĥİ

-0.73

ETS

-0.73

MET

-0.72

idelines

-0.71

WAY

-0.70

ouls

-0.70

POSITIVE LOGITS

 vice

0.95

 consequently

0.84

 grandson

0.84

 therefore

0.80

 longtime

0.78

 organizer

0.77

 oversaw

0.76

 outspoken

0.76

 fellow

0.74

 colleague

0.73

Activations Density 0.273%

names of individuals and their titles or roles

coordinating conjunctions, particularly "and."

No Comments

No Known Activations