INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "pin"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Explicit

-0.69

 cleaners

-0.66

 Clean

-0.66

 adequ

-0.66

 Healthcare

-0.65

 cleanup

-0.64

wa

-0.61

 bathrooms

-0.60

 Horses

-0.60

 survivors

-0.59

POSITIVE LOGITS

pin

4.78

pins

3.15

PIN

2.14

Pin

1.87

pin

1.52

Pin

1.52

pine

1.50

 pins

1.36

pen

1.14

peed

1.13

Activations Density 0.008%

proper nouns

occurrences of the word "pin"

No Comments

No Known Activations