INDEX

Explanations

words related to information being received or incoming

oai_token-act-pair · gpt-3.5-turbo

instances of the word "incoming."

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

arist

-0.84

trak

-0.77

ching

-0.76

 Trance

-0.76

arily

-0.75

mel

-0.75

lance

-0.74

agra

-0.74

FactoryReloaded

-0.69

Dur

-0.69

POSITIVE LOGITS

 freshmen

0.91

 incoming

0.84

 arrivals

0.81

 freshman

0.79

 outgoing

0.79

ãģŁ

0.73

ãĤĬ

0.70

 arrival

0.68

 generation

0.68

 commissions

0.68

Activations Density 0.016%

words related to information being received or incoming

instances of the word "incoming."

No Comments

No Known Activations