INDEX

Explanations

locations or directions within a context

oai_token-act-pair · gpt-3.5-turbo

instances of the word "where" indicating location or placement

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ATURE

-0.87

yi

-0.72

ilus

-0.70

ME

-0.70

astics

-0.69

vous

-0.66

agers

-0.66

asts

-0.64

UX

-0.63

bart

-0.63

POSITIVE LOGITS

abouts

1.29

upon

1.14

fore

1.00

 else

0.89

soever

0.86

 exactly

0.78

velt

0.72

 nearest

0.70

ngth

0.67

 Prescott

0.66

Activations Density 0.044%

locations or directions within a context

instances of the word "where" indicating location or placement

No Comments

No Known Activations