INDEX

Explanations

proper nouns related to specific locations, particularly Albany and Luxembourg

oai_token-act-pair · gpt-3.5-turbo

locations, particularly focusing on the cities of Albany and Luxembourg

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

lett

-0.85

osate

-0.85

lication

-0.78

liness

-0.77

riages

-0.74

iak

-0.74

mares

-0.74

acco

-0.71

²¾

-0.70

ously

-0.70

POSITIVE LOGITS

lehem

0.77

gdala

0.76

 Schumer

0.71

PRESS

0.67

ngth

0.66

roth

0.66

 Tanz

0.65

Nir

0.64

press

0.63

sson

0.60

Activations Density 0.039%

proper nouns related to specific locations, particularly Albany and Luxembourg

locations, particularly focusing on the cities of Albany and Luxembourg

No Comments

No Known Activations