INDEX

Explanations

references to geographic locations, specifically "Northern"

oai_token-act-pair · gpt-3.5-turbo

references to "Northern" regions or entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

verb

-0.89

ulative

-0.86

inventoryQuantity

-0.85

earance

-0.83

ATURE

-0.82

iatrics

-0.78

inger

-0.78

enance

-0.76

 Machina

-0.74

enger

-0.73

POSITIVE LOGITS

 Hemisphere

1.12

 hemisphere

1.05

 Lights

0.98

 Territory

0.97

 Ireland

0.88

 Liberties

0.84

 Territories

0.79

most

0.77

 Caucasus

0.77

vale

0.74

Activations Density 0.018%

references to geographic locations, specifically "Northern"

references to "Northern" regions or entities

No Comments

No Known Activations