INDEX

Explanations

phrases related to spatial orientation and physical attributes like shape, speed, and style

oai_token-act-pair · gpt-3.5-turbo

phrases related to measurement or scale 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

NetMessage

-0.68

iolet

-0.66

arna

-0.66

 Maple

-0.63

BIP

-0.62

onis

-0.62

terday

-0.62

ãĤĵ

-0.62

ce

-0.62

****************

-0.61

POSITIVE LOGITS

forts

0.69

achu

0.68

antry

0.67

 equivalent

0.67

same

0.67

liest

0.66

 usual

0.66

of

0.63

 natives

0.63

 opposite

0.61

Activations Density 0.150%

phrases related to spatial orientation and physical attributes like shape, speed, and style

phrases related to measurement or scale in various contexts

No Comments

No Known Activations