INDEX

Explanations

references to the location "Abercynon"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the prefix "non-" indicating negation or absence

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 charts

-0.75

bow

-0.71

 scene

-0.67

 stacks

-0.66

 sooner

-0.66

 height

-0.64

 promise

-0.64

 yards

-0.63

 precip

-0.63

 towers

-0.62

POSITIVE LOGITS

non

3.89

Non

2.21

NON

1.66

Non

1.66

non

1.48

no

1.43

nan

1.20

nos

1.17

anti

1.14

not

1.10

Activations Density 0.013%

references to the location "Abercynon"

occurrences of the prefix "non-" indicating negation or absence

No Comments

No Known Activations