INDEX

Explanations

words related to loss or things being lost

oai_token-act-pair · gpt-3.5-turbo

instances of the word "lost" in various contexts

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

osi

-0.80

ansky

-0.78

 barr

-0.69

ricks

-0.68

sis

-0.68

deen

-0.64

INC

-0.64

erity

-0.63

 prepared

-0.62

ocr

-0.62

POSITIVE LOGITS

 souls

0.93

 Souls

0.93

hearted

0.80

luster

0.76

lust

0.75

 sight

0.74

erness

0.74

 innocence

0.70

 soul

0.67

itive

0.67

Activations Density 0.020%

words related to loss or things being lost

instances of the word "lost" in various contexts

No Comments

No Known Activations