INDEX

Explanations

proper nouns representing people or locations

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals and characters

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GoldMagikarp

-0.68

earcher

-0.67

inth

-0.66

atform

-0.65

-+-+

-0.65

VERTISEMENT

-0.63

ources

-0.62

uitive

-0.62

etheless

-0.61

Compare

-0.61

POSITIVE LOGITS

Jr

1.30

Sr

0.98

III

0.92

QC

0.91

aka

0.84

burgh

0.80

otti

0.79

PhD

0.78

 Architects

0.78

opoulos

0.77

Activations Density 0.450%

proper nouns representing people or locations

proper nouns, particularly names of individuals and characters

No Comments

No Known Activations