INDEX

Explanations

locations and specific places

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically geographical locations and notable landmarks

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

 ãĤµ

-0.69

 meantime

-0.68

ãĥĸ

-0.67

 Nich

-0.66

 Manga

-0.65

Topic

-0.62

 underrated

-0.61

 McKin

-0.60

 differently

-0.60

ãĤ°

-0.59

POSITIVE LOGITS

 horizon

0.87

antage

0.78

 cliffs

0.77

 boundaries

0.77

 confines

0.74

ifice

0.73

 axis

0.73

 entrance

0.72

bearing

0.70

illon

0.69

Activations Density 0.615%

locations and specific places

proper nouns, specifically geographical locations and notable landmarks

No Comments

No Known Activations