INDEX

Explanations

locations or establishments where events or incidents occur

oai_token-act-pair · gpt-3.5-turbo

the article "a" preceding various nouns and phrases

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Rules

-0.74

 Thumbnails

-0.66

Either

-0.66

hesis

-0.66

coins

-0.66

Order

-0.66

Contents

-0.66

 Articles

-0.65

 Effect

-0.65

rules

-0.65

POSITIVE LOGITS

 nearby

1.16

 reputable

1.07

 defunct

1.07

 local

1.03

 neighboring

1.01

 prestigious

0.96

 boutique

0.93

 cafÃ©

0.92

 nonprofit

0.91

 prominent

0.90

Activations Density 0.287%

locations or establishments where events or incidents occur

the article "a" preceding various nouns and phrases

No Comments

No Known Activations