INDEX

Explanations

phrases related to the concept of location or direction

oai_token-act-pair · gpt-3.5-turbo

questions and statements regarding locations or positions

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

emed

-0.74

quel

-0.72

ATURE

-0.72

apt

-0.71

MER

-0.69

asts

-0.68

advertisement

-0.67

bart

-0.66

icum

-0.64

ME

-0.63

POSITIVE LOGITS

abouts

1.23

upon

1.05

 else

1.04

 exactly

0.97

fore

0.88

ver

0.82

soever

0.81

 they

0.72

 nearest

0.66

we

0.63

Activations Density 0.041%

phrases related to the concept of location or direction

questions and statements regarding locations or positions

No Comments

No Known Activations