INDEX

Explanations

direct requests or instructions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "to" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nox

-0.71

browser

-0.69

ahime

-0.68

hur

-0.64

quickShipAvailable

-0.64

til

-0.58

 futures

-0.58

fortunately

-0.56

Apps

-0.56

hop

-0.56

POSITIVE LOGITS

 participate

1.07

 undergo

1.00

 perform

0.93

 provide

0.92

 proceed

0.92

 partake

0.91

 carry

0.91

 attend

0.91

pless

0.90

 undertake

0.89

Activations Density 0.161%

direct requests or instructions

instances of the word "to" in various contexts

No Comments

No Known Activations