INDEX

Explanations

terms related to the setup of different entities or activities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "setup" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

orie

-0.77

thood

-0.76

 ILCS

-0.73

ilee

-0.71

hig

-0.71

onso

-0.70

pha

-0.70

angible

-0.69

Ago

-0.69

irth

-0.68

POSITIVE LOGITS

 setups

1.00

 setup

0.96

eers

0.86

eering

0.85

setup

0.79

 Setup

0.79

 configurations

0.74

 routines

0.70

creen

0.69

ession

0.69

Activations Density 0.010%

terms related to the setup of different entities or activities

instances of the word "setup" in various contexts

No Comments

No Known Activations