INDEX

Explanations

phrases related to automobile components and operations, such as door seals, driver's licenses, and safety systems

oai_token-act-pair · gpt-3.5-turbo

terms related to legal and driving contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

jri

-0.83

yip

-0.79

achus

-0.77

iland

-0.75

urat

-0.73

ibaba

-0.70

 grapes

-0.68

soType

-0.67

ashtra

-0.67

phrine

-0.66

POSITIVE LOGITS

command

0.79

operated

0.75

execute

0.74

Command

0.71

ĳå£«

0.67

 Commands

0.67

Cmd

0.67

 command

0.66

BILITIES

0.64

 remotely

0.64

Activations Density 0.672%

phrases related to automobile components and operations, such as door seals, driver's licenses, and safety systems

terms related to legal and driving contexts

No Comments

No Known Activations